alt.freeweights.mistral / Ministral-3-3B-Instruct-2512-ONNX
From: mistralai <huggingface.co/mistralai>Newsgroups: alt.freeweights.mistralSubject:

Ministral-3-3B-Instruct-2512-ONNX

Date: 2026-11-15Commit: e1128d3Signed: 2DC28CC7B26A283B ✓

Image text to text model. Onnx weights, 36.3 GB in all. Published by mistralai under Apache-2.0.

mistral36.3GBMinistral-3-3B-Instruct-2512-ONNXonnxpermissive
FactsParamsnot statedSize36.3 GBFormatsonnxTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mistralai/Ministral-3-3B-Instruct-2512-ONNX
# manifest sha256 b55057d9fa1e… · 36.3 GB · 51 files
$ fw verify ./Ministral-3-3B-Instruct-2512-ONNX mistralai/Ministral-3-3B-Instruct-2512-ONNX
From sourceHosted (signed)mistralai/Ministral-3-3B-Instruct-2512-ONNXLast check: 2026-11-15 05:06 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of Ministral-3-3B-Instruct-2512.

Works with

Runs with

Ranked by fit to this model (onnx), then by GitHub stars.

Convert with

Overview

Size
36.3 GB
Weights
244 MB (smallest of 15 ONNX variants)
Parameters
not stated
Formats
onnx
Task
image text to text
License
Apache-2.0 (permissive)
Files
51, each with a sha256
Publisher
mistralai
Added
2026-11-15
Section
alt.freeweights.mistral
Lineage

Original release from the publisher.

Base model: mistralai/Ministral-3-3B-Instruct-2512

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:06 UTCpassed

Model card

From the publisher at commit e1128d3. Shown as plain text with links; images open at the publisher.

Tip. This model was contributed by Xenova from Hugging Face. We sincerely appreciate the integration and community collaboration. While preliminary functionality checks have been performed, comprehensive testing has not yet been completed. We recommend you to proceed with caution and conducting your own evaluations for specific use cases. If any issues arise, open a PR/Issue here and we will try to address them promptly.

Ministral 3 3B Instruct 2512 ONNX#

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

This model quantized weights of the instruct post-trained version in ONNX, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 3B can even be deployed locally, capable of fitting in 8GB of VRAM in FP8, and less if further quantized.

Learn more in our blog post and paper.

Key Features#

Ministral 3 3B consists of two main architectural components:

  • 3.4B Language Model
  • 0.4B Vision Encoder

The Ministral 3 3B Instruct model offers the following capabilities:

  • Vision: Enables the model to analyze images and provide insights based on visual content, in addition to text.
  • Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
  • System Prompt: Maintains strong adherence and support for system prompts.
  • Agentic: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
  • Edge-Optimized: Delivers best-in-class performance at a small scale, deployable anywhere.
  • Apache 2.0 License: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
  • Large Context Window: Supports a 256k context window.

Usage#

Transformers.js#
Online WebGPU Demo#

You can test out the model directly in your browser using our online WebGPU demo: https://huggingface.co/spaces/mistralai/Ministral_3B_WebGPU.

JavaScript#

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

You can then run the model as follows:

import {
    AutoProcessor,
    AutoModelForImageTextToText,
    load_image,
    TextStreamer,
} from "@huggingface/transformers";

// Load processor and model
const model_id = "mistralai/Ministral-3-3B-Instruct-2512-ONNX";
const processor = await AutoProcessor.from_pretrained(model_id);
const model = await AutoModelForImageTextToText.from_pretrained(model_id, {
    device: "webgpu",
});

// Prepare inputs
const messages = [
    {
        role: "user",
        content: [
            { type: "image" },
            {
                type: "text",
                text: "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
        ],
    },
]
const prompt = processor.apply_chat_template(messages);
const url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438";
const image = await load_image(url);
const inputs = await processor(image, prompt, { add_special_tokens: false });

// Generate response
const outputs = await model.generate({
    ...inputs,
    max_new_tokens: 2048,
    streamer: new TextStreamer(processor.tokenizer, {
        skip_prompt: true,
        // callback_function: (text) => { /* Do something with the streamed output */ },
    }),
});

// Decode output
const decoded = processor.batch_decode(
    outputs.slice(null, [inputs.input_ids.dims.at(-1), null]),
    { skip_special_tokens: true },
);
console.log(decoded[0]);

See example output

In this Pokémon game screenshot, you have several potential actions to consider, depending on the situation and your strategy. Here are the possible actions and their implications:

---

### **1. FIGHT**
**Description:** Use the Pikachu in your possession to attack the Pidgey.

#### **Pros:**
- **Potential to defeat Pidgey:** If Pikachu has strong moves (e.g., Thunderbolt, Electric Move) and Pidgey is weak to Electric-type attacks, this could be a strong choice.
- **Experience Gain:** Winning battles typically rewards you with experience points (XP) and sometimes drops Pidgey as a captured Pokémon.
- **Training Opportunity:** Helps you level up Pikachu, which can improve its stats and access new moves.

#### **Cons:**
- **Risk of Losing Pikachu:** If Pikachu is already at a low HP (e.g., 83/83 is not bad, but if it's lower), a loss could be detrimental.
- **Move Selection Matters:** If Pikachu doesn’t have a strong move against Pidgey, you might lose the battle unnecessarily.
- **Stamina Cost:** Battles can consume stamina if you're on a timer-based system (e.g., Pokémon Red/Blue).

---

### **2. RUN**
**Description:** Use the "Run" option to escape the battle.

#### **Pros:**
- **Avoids Risk:** If you're unsure about Pikachu’s moves or HP, running could save you from a potentially bad outcome.
- **Preserves Resources:** Running avoids losing Pikachu’s HP, which could be useful if you're running low.
- **Flexibility:** Allows you to explore or use other Pokémon later.

#### **Cons:**
- **No XP Gain:** Running means you won’t earn XP for defeating Pidgey.
- **Potential Consequences:** If you run too often, you might miss out on capturing Pidgey or gaining experience.
- **No Training:** Pikachu won’t level up or gain new moves if you avoid battles.

---

### **3. POKEMON (Select Another Pokémon)**
**Description:** If you have another Pokémon in your party, you could switch to it.

#### **Pros:**
- **Better Move Selection:** If you have a stronger Pokémon (e.g., a Fire-type or Ground-type) that can handle Pidgey, switching could be beneficial.
- **Balanced Strategy:** Helps you manage your team better.
- **Avoids Weaknesses:** If Pikachu is weak to something Pidgey might use, switching could prevent a loss.

#### **Cons:**
- **No Immediate XP Gain:** Switching doesn’t defeat Pidgey, so you won’t earn XP.
- **Stamina Cost:** Switching might still consume stamina if you're on a timer.
- **Potential to Lose Pikachu:** If you switch and Pikachu is already at a low HP, you might lose it.

---

### **Best Strategy Based on the Image:**
- **If you want to capture Pidgey:** Fighting is the best option, as it rewards you with experience and potentially captures Pidgey.
- **If you're unsure about Pikachu’s moves:** Running could be safer, but you might miss out on XP.
- **If you have another Pokémon:** Switching could be a good idea if you have a stronger option.

Would you like to know what moves Pikachu might have, or do you have another Pokémon in your party? That could help decide the best action!
ONNXRuntime#
from transformers import AutoConfig, AutoProcessor
import onnxruntime
import numpy as np
from huggingface_hub import hf_hub_download

# 1. Load config, processor, and model
model_id = "mistralai/Ministral-3-3B-Instruct-2512-ONNX"
config = AutoConfig.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

vision_model_path = hf_hub_download(model_id, "vision_encoder_q4.onnx", subfolder="onnx")         # Download vision graph
hf_hub_download(model_id, "vision_encoder_q4.onnx_data", subfolder="onnx")                        # Download vision weights
embed_model_path = hf_hub_download(model_id, "embed_tokens_fp16.onnx", subfolder="onnx")          # Download embed_tokens graph
hf_hub_download(model_id, "embed_tokens_fp16.onnx_data", subfolder="onnx")                        # Download embed_tokens weights
decoder_model_path = hf_hub_download(model_id, "decoder_model_merged_q4.onnx", subfolder="onnx")  # Download decoder graph
hf_hub_download(model_id, "decoder_model_merged_q4.onnx_data", subfolder="onnx")                  # Download decoder weights (1/2)
hf_hub_download(model_id, "decoder_model_merged_q4.onnx_data_1", subfolder="onnx")                # Download decoder weights (2/2)

## Load sessions
providers = ['CPUExecutionProvider']
vision_session = onnxruntime.InferenceSession(vision_model_path, providers=providers)
embed_session = onnxruntime.InferenceSession(embed_model_path, providers=providers)
decoder_session = onnxruntime.InferenceSession(decoder_model_path, providers=providers)

## Set config values
text_config = config.text_config
num_key_value_heads = text_config.num_key_value_heads
head_dim = text_config.head_dim
num_hidden_layers = text_config.num_hidden_layers
eos_token_id = text_config.eos_token_id
image_token_index = config.image_token_index

# 2. Prepare inputs
image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
            {"type": "image", "url": image_url},
        ],
    },
]
inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt")

input_ids = inputs['input_ids'].numpy()
attention_mask = inputs['attention_mask'].numpy()
pixel_values = inputs['pixel_values'].numpy()
batch_size = input_ids.shape[0]
past_key_values = {
    f'past_key_values.{layer}.{kv}': np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32)
    for layer in range(num_hidden_layers)
    for kv in ('key', 'value')
}
position_ids = np.tile(np.arange(0, input_ids.shape[-1]), (batch_size, 1))

# 3. Generation loop
max_new_tokens = 1024
generated_tokens = np.array([[]], dtype=np.int64)
image_features = None
for i in range(max_new_tokens):
  inputs_embeds = embed_session.run(None, {'input_ids': input_ids})[0]

  if image_features is None:
    ## Only compute vision features if not already computed
    image_features = vision_session.run(None, dict(
        pixel_values=pixel_values,
    ))[0]

    ## Merge text and vision embeddings
    inputs_embeds[input_ids == image_token_index] = image_features.reshape(-1, image_features.shape[-1])

  logits, *present_key_values = decoder_session.run(None, dict(
      inputs_embeds=inputs_embeds,
      attention_mask=attention_mask,
      position_ids=position_ids,
      **past_key_values,
  ))

  ## Update values for next generation loop
  input_ids = logits[:, -1].argmax(-1, keepdims=True)
  attention_mask = np.concatenate([attention_mask, np.ones((batch_size, 1), dtype=attention_mask.dtype)], axis=-1)
  position_ids = position_ids[:, -1:] + 1
  for j, key in enumerate(past_key_values):
    past_key_values[key] = present_key_values[j]

  generated_tokens = np.concatenate([generated_tokens, input_ids], axis=-1)
  if (input_ids == eos_token_id).all():
    break

  ## (Optional) Streaming
  print(processor.decode(input_ids[0]), end='', flush=True)
print()

# 4. Output result
print(processor.batch_decode(generated_tokens, skip_special_tokens=True)[0])

See example output

In this *Pokémon* game screenshot, you are presented with a battle scenario between **Pidgey** and **Pikachu**. Here are the possible actions along with an analysis of their potential outcomes:

---

### **1. FIGHT**
**Explanation:**
- You choose to engage in battle.
- Pidgey is a **Level 17** Pokémon with basic stats, while Pikachu is a **Level 42** Pokémon with significantly higher HP, Attack, and overall power.
- **Pros:**
  - Pikachu is stronger and likely to win if it lands a hit.
  - Pidgey may be able to land a few moves before being overwhelmed.
- **Cons:**
  - Pidgey is likely to lose quickly due to its lower stats and experience.
  - Pikachu may have a high chance of winning in one or two turns.

---

### **2. BAG**
**Explanation:**
- You choose to **Bag** Pikachu.
- **Pros:**
  - You can keep Pikachu in your bag for later use.
  - If you need to switch Pokémon or use Pikachu in another battle, this is a viable option.
- **Cons:**
  - You miss out on the opportunity to potentially defeat Pidgey and gain experience.
  - If Pidgey is a rare or special Pokémon, bagging it might not be ideal.

---

### **3. RUN**
**Explanation:**
- You choose to **Run** (escape the battle).
- **Pros:**
  - You avoid losing HP and experience points.
  - You can continue your journey without facing a weaker opponent.
- **Cons:**
  - You might miss out on a chance to level up Pikachu or gain experience.
  - If you are in a competitive setting, running might not be the best strategy.

---

### **Summary of Best Options:**
- **If you want to continue the game and gain experience:**
  - **Fight** Pikachu, but be prepared for a potentially quick loss.
- **If you want to save Pikachu for later:**
  - **Bag** Pikachu and continue your journey.
- **If you want to avoid unnecessary battles:**
  - **Run** away from the battle.

Since Pikachu is significantly stronger, **Fighting** is the most straightforward choice, but you might want to consider **Bagging** Pikachu if you want to keep it for later battles. If you're not in a rush, **Running** is also a viable option.
In this *Pokémon* game screenshot, you are presented with a battle scenario between **Pidgey** and **Pikachu**. Here are the possible actions along with an analysis of their potential outcomes:

---

### **1. FIGHT**
**Explanation:**
- You choose to engage in battle.
- Pidgey is a **Level 17** Pokémon with basic stats, while Pikachu is a **Level 42** Pokémon with significantly higher HP, Attack, and overall power.
- **Pros:**
  - Pikachu is stronger and likely to win if it lands a hit.
  - Pidgey may be able to land a few moves before being overwhelmed.
- **Cons:**
  - Pidgey is likely to lose quickly due to its lower stats and experience.
  - Pikachu may have a high chance of winning in one or two turns.

---

### **2. BAG**
**Explanation:**
- You choose to **Bag** Pikachu.
- **Pros:**
  - You can keep Pikachu in your bag for later use.
  - If you need to switch Pokémon or use Pikachu in another battle, this is a viable option.
- **Cons:**
  - You miss out on the opportunity to potentially defeat Pidgey and gain experience.
  - If Pidgey is a rare or special Pokémon, bagging it might not be ideal.

---

### **3. RUN**
**Explanation:**
- You choose to **Run** (escape the battle).
- **Pros:**
  - You avoid losing HP and experience points.
  - You can continue your journey without facing a weaker opponent.
- **Cons:**
  - You might miss out on a chance to level up Pikachu or gain experience.
  - If you are in a competitive setting, running might not be the best strategy.

---

### **Summary of Best Options:**
- **If you want to continue the game and gain experience:**
  - **Fight** Pikachu, but be prepared for a potentially quick loss.
- **If you want to save Pikachu for later:**
  - **Bag** Pikachu and continue your journey.
- **If you want to avoid unnecessary battles:**
  - **Run** away from the battle.

Since Pikachu is significantly stronger, **Fighting** is the most straightforward choice, but you might want to consider **Bagging** Pikachu if you want to keep it for later battles. If you're not in a rush, **Running** is also a viable option.

License#

This model is licensed under the Apache 2.0 License.

You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.

Files

51 files · 36.3 GBWeights 244 MB (smallest of 15 ONNX variants). Sizes and sha256 from the signed manifest.
Show all 51 files with their sha256
FileSizesha256
.gitattributes3.49 KB1251ea4591f94f6fa4fa67b6ae80aafc9dfef741c04b9be54a187343f67e3eef
README.md16.5 KBe3451a12a253f4b2d76741910a12663d124f53deba69ce3e2ee35c29eb9f083b
chat_template.jinja7.75 KBd28d7df94f0fd7e8d0075a22c473333d6e7dd2bc4c36c83e8b975300a0fb94bc
config.json3.08 KB4a05c7ddaced59b8c42e6f6dedd7ad5a59493931f313575d434eae667418d15a
generation_config.json161 Bd8794dd66e643c2972dbe490028ee5805592ffea33cc197679ffd3d113313f27
onnx/decoder_model_merged.onnx210 KB52bc3d8c9352a18701b66584d65623486b4d2f49d320c1f1c66b2afd12f7b3de
onnx/decoder_model_merged.onnx_data2.07 GBea46d55ec62ca9355d97e5be1c128246163007f16aef0685d3ff833247846ccd
onnx/decoder_model_merged.onnx_data_12.03 GBfa33e3a5c3ee4971bf495e63b2bd2d037347c286012c39406cdb8bf55555468a
onnx/decoder_model_merged.onnx_data_22.09 GB7bfda146c48d32f5a1e3345607bce3c4e26c26cceb4ca5af80f24ed3c5c44181
onnx/decoder_model_merged.onnx_data_31.99 GB6f76ca0445b7a5086697553c7366c7d95f34d6b28454496a1bb6d7b6974438fa
onnx/decoder_model_merged.onnx_data_42.09 GB8821419c29e9eb615593f80608ee232dd28308067c878c5e2e5429aa2564ccbb
onnx/decoder_model_merged.onnx_data_51.98 GB5728688f573c0953c7e757dcc53ac29c305fb910ffde59f364abed8f01d4d76e
onnx/decoder_model_merged.onnx_data_61.61 GBb576927ad3062f7128f8617225d6f48eee8df6d22d54de7257c6ab273939c662
onnx/decoder_model_merged_fp16.onnx212 KB901c97b50208af3026d3c61c660a10c4f3372c2545f3fb511688e81aa6bae57e
onnx/decoder_model_merged_fp16.onnx_data2.05 GB0095e83a7e5cfb66c2bd12eefe328f6e0155c0d4e1aee27e6afa858133a5f5c9
onnx/decoder_model_merged_fp16.onnx_data_12.10 GB348c0df191753af9b4c412446019857617bc37ab4ce51d088e6af5c1ec06007c
onnx/decoder_model_merged_fp16.onnx_data_21.98 GB947a09208300d55f9e71e49d698b79a622797f02e9ad8db0ab7ef088301ee528
onnx/decoder_model_merged_fp16.onnx_data_3805 MB1661404d365a0f7a58086c47fb17028f6a51957b641c1ce9ecc0046371fe8873
onnx/decoder_model_merged_q4.onnx280 KB3f60434cd9cb5b6c85ec1e4c6a4d6c7705bce7bf266f86bfb4b1150757f17349
onnx/decoder_model_merged_q4.onnx_data2.03 GB14e1aa9933d5844137758e08b78db04cdb7e8c93130eb829fa3b4d93475031ea
onnx/decoder_model_merged_q4.onnx_data_1252 MBfd75a8bf45733ed4643a9015a326412509d9aa544951a8064b6962f6038bcb7d
onnx/decoder_model_merged_q4f16.onnx282 KB9e591109067dcc9efc1b14daaa6e0e78ed917f03ff242a3a1bf4e3bc13478a56
onnx/decoder_model_merged_q4f16.onnx_data2.00 GBd5985999bc1755741860a1cf4838549f381bc5d32eb09379add5ee60f0282dd2
onnx/decoder_model_merged_quantized.onnx304 KBba1647c36b755ebefd673f2f3fe88ec07411be4b67299046f1de9948a4675727
onnx/decoder_model_merged_quantized.onnx_data2.09 GB2e4e8f505101d39c228e7bd7cde4b79a11a2f45ede996fd2094c78478a9b0778
onnx/decoder_model_merged_quantized.onnx_data_12.01 GB02d963723ef2641a2009eec99fc45c2f935c0506381c2828a2063d4c39dd7fd4
onnx/embed_tokens.onnx435 Bc8da5ab11bdc58efa6773d9a460e44a7c0c3c84b7cbf5b4fe2d92cb524fc78b5
onnx/embed_tokens.onnx_data1.61 GBd0a4bd0cc78127a6ee850705edef737a7096b7588d018ef23abe4afc0c5ee6e3
onnx/embed_tokens_fp16.onnx637 Be6ffa9413b01686ee57236ccb8606ce7feb784910a1d764103d64cb70271b9ef
onnx/embed_tokens_fp16.onnx_data805 MB623599b346068db9c32d2e6fc3c5157ee7d5d48491670aa2c32d4a2a373af6dd
onnx/embed_tokens_q4.onnx857 B202fb30fc3b9fd508f80ad63e6040fc38b774a75a5a3c114f27a0f910f69a915
onnx/embed_tokens_q4.onnx_data258 MBe3add6de40eb3b8eee4c9cd9f27fbfa258f7319365854b02360d8f3ae2cf16f0
onnx/embed_tokens_q4f16.onnx1.06 KBbab0a291678334b4463d0d5c6e65fbcc1169fea9c1ebcbb849176c4e1baaf8de
onnx/embed_tokens_q4f16.onnx_data440 MBa0c032f7d6a902861b58b9f2432a6f9128ecc0c0e85bffed3089972ccc60f96b
onnx/embed_tokens_quantized.onnx880 Bbb1086281df37baba3a4a230e70692a2e0d4aaa178ca6af1ee7065c1104cebcf
onnx/embed_tokens_quantized.onnx_data466 MB584e5797d01d3a391bd662d8e7a661be183b7f7ab2dd92688da1b97565808b0a
onnx/vision_encoder.onnx247 KB20a5d7cf6a6dd78a0d9b006bbef816c43f8b01566d3b1aa0aa4366a74881bba0
onnx/vision_encoder.onnx_data1.68 GB7ba4885cf93391ffeb1b4e5503112bf5c0f61c241e95614792b5c1c8a6721e28
onnx/vision_encoder_fp16.onnx248 KB0ab775e109e63c8cd352e5f5fb7c88cab62798c6c82be82b8c997150614b9be2
onnx/vision_encoder_fp16.onnx_data840 MBb0e2a922b9bc2675a05210cccd75950ffd0ab45cf9eaa370223c41a162e18b49
onnx/vision_encoder_q4.onnx327 KBc0daf54a4f6956205cc66945d427684919c4ba6c14758ba91246a5451f8de43c
onnx/vision_encoder_q4.onnx_data271 MB3e37bf50a639889b1abae0f2d9624fee388f013f675f55e1ca66b8abb39a0552
onnx/vision_encoder_q4f16.onnx329 KBbd56a2c97d435c057f7b42493333dd10fa4a9631b5c46a10355e7c3df870e951
onnx/vision_encoder_q4f16.onnx_data244 MB9bfb701b5345939e3ca51b0c938511943f2b6672f12d696e36252154c76b9d4f
onnx/vision_encoder_quantized.onnx331 KBdf36568639c697d9d141b8edadc49a1681edba291306a8ff893cf5715d03f08e
onnx/vision_encoder_quantized.onnx_data488 MBe07528953ced8388f2daa7df28fdb22107ea76c80644667884c4ec4757e477ae
preprocessor_config.json725 B024f298d4ecc5f2e599bbe555f758baa3603f0388a6456bd04a66d3e2d36fd9e
processor_config.json976 Bece2373c2ae391bce18785a1810543bc6173a1f28b6767cffab2c35dbea5f002
special_tokens_map.json21.4 KB6fed0bd0e17f675bf035e1a63966da715a44c7d87a7bb47ab767814d5ffc2c8b
tokenizer.json12.6 MBfa0cdf170403fdfe173ebb7356b0443d3f3908aeed183d24712a0410631540f2
tokenizer_config.json206 KB8e0096c9c11500fd6230c38408ad53fd926ab2408057bf3421839cfd6082bc21
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e1128d3891 pinned now2026-11-15 05:06 UTC51 files · 36.3 GB

Use it

$ fw get mistralai/Ministral-3-3B-Instruct-2512-ONNX
# manifest sha256 b55057d9fa1e… · 36.3 GB · 51 files
$ fw verify ./Ministral-3-3B-Instruct-2512-ONNX mistralai/Ministral-3-3B-Instruct-2512-ONNX
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mistralai/Ministral-3-3B-Instruct-2512-ONNX.json --dir ./Ministral-3-3B-Instruct-2512-ONNX $ python3 fw.py verify ./Ministral-3-3B-Instruct-2512-ONNX ./mistralai__Ministral-3-3B-Instruct-2512-ONNX.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mistralai/Ministral-3-3B-Instruct-2512-ONNX --revision e1128d389145f96bb1c3c2625cb8ca255ffa7034 --local-dir ./Ministral-3-3B-Instruct-2512-ONNX

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
e3451a12a253f4b2d76741910a12663d124f53deba69ce3e2ee35c29eb9f083b
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: mistralai <huggingface.co/mistralai>Newsgroups: alt.freeweights.mistralSubject: Ministral-3-3B-Instruct-2512-ONNXDate: 2026-11-15Commit: e1128d3Signed: 2DC28CC7B26A283B ✓
Upstream
mistralai/Ministral-3-3B-Instruct-2512-ONNX
Pinned commit
e1128d389145f96bb1c3c2625cb8ca255ffa7034
Manifest
Ministral-3-3B-Instruct-2512-ONNX.json · .minisig
Manifest sha256
b55057d9fa1ea9db29d9434d639c6671a2e8e54a50d013ecedaaff67c9df1990
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:06 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mistralai/Ministral-3-3B-Instruct-2512-ONNX.json $ curl -O https://freeweights.allternit.com/manifests/mistralai/Ministral-3-3B-Instruct-2512-ONNX.json.minisig $ minisign -Vm Ministral-3-3B-Instruct-2512-ONNX.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

mistralai/Ministral-3-3B-Instruct-2512 · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mistralai/Ministral-3-3B-Instruct-2512-ONNX
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Ministral-3-3B-Instruct-2512-ONNX.json. Provenance. Takedown history: none.
From: bartowski <huggingface.co/bartowski>Subject: alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF
From: microsoft <huggingface.co/microsoft>Subject: chatbench-mistral-7b
From: NousResearch <huggingface.co/NousResearch>Subject: DeepHermes-3-Mistral-24B-Preview
From: mistralai <huggingface.co/mistralai>Subject: Devstral-Small-2-24B-Instruct-2512
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-4bit
From: mlx-community <huggingface.co/mlx-community>Subject: Devstral-Small-2-24B-Instruct-2512-6bit