From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-R1-Distill-Qwen-32B-4bit Date: 2026-11-14Commit: 4e0d384Signed: 2DC28CC7B26A283B ✓ Text generation model with 32.8B parameters. Safetensors weights, 18.4 GB in all. Published by mlx-community under MIT.
32.8B params 18.4 GB DeepSeek-R1-Distill-Qwen-32B-4bit safetensors permissive Facts Params 32.8B Size 18.4 GB Formats safetensors Task text generation License MIT permissive
fw
$ fw get mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit
# manifest sha256 c3275245e03f… · 18.4 GB · 11 files
$ fw verify ./DeepSeek-R1-Distill-Qwen-32B-4bit mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bitHosted (signed) mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit Last check: 2026-11-14 21:29 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of DeepSeek-R1-Distill-Qwen-32B .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 18.4 GB
Weights 18.4 GB (safetensors)
Parameters 32.8B
Formats safetensors
Task text generation
License MIT (permissive)
Files 11, each with a sha256
Publisher mlx-community
Added 2026-11-14
Section alt.freeweights.deepseek Lineage
Original release from the publisher.
Base model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
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
Badge Host Last check Result huggingface.co 2026-11-14 21:29 UTC passed
Model card From the publisher at commit
4e0d384 . Shown as plain text with links; images open at the publisher.
The Model mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B using mlx-lm version 0.20.2 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True) Files 11 files · 18.4 GB Weights 18.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 11 files with their sha256 File Size sha256 .gitattributes 1.57 KB 34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930 README.md 967 B d07ed184a2a36eb3164422a69e5d71749c8818d62168346fcce5c0ee7702e320 config.json 868 B 7d68c4249ba48a515ea8b766867dd1929f9cbe1b17ba410beb1bb5aa2b14288c model-00001-of-00004.safetensors 5.37 GB b152d90eb4f3439375b83da342647c065ab5619d2eded96768ec78736ea3f2d8 model-00002-of-00004.safetensors 5.34 GB ef98d21f284cf8e4fcc60fd4b28ddca6da01d9bc153cdf699795ad6402b76d6d model-00003-of-00004.safetensors 5.37 GB b0bdb70116ae2806e95017e73a10df766e15a01cb94023100a43ac2693fcd43c model-00004-of-00004.safetensors 2.36 GB e68c26b406383e00f2b6821613f4fd0e5a4708c88c3af8fef29a89d64e0bde21 model.safetensors.index.json 143 KB 7b6da9b2b1f3ebd698ae15f9fcf6ba3099e742ec07e5d383f28b7cb77a4d16db special_tokens_map.json 485 B 59cda48bbe8bab9d61ffb410e6e3c07b6d98bff73cee7c88ff8b51f95f21ab1c tokenizer.json 11.4 MB e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 tokenizer_config.json 6.76 KB d9125f504eea1bb56c8bb7cfa32ae9b782ab8e0fc59a5cd58d1ef7728fb61273
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 4e0d3848a0 pinned now manifest updated, same commit 2026-11-14 21:29 UTC 11 files · 18.4 GB 4e0d3848a0 2026-11-14 21:29 UTC 11 files · 18.4 GB
Use it fw
$ fw get mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit
# manifest sha256 c3275245e03f… · 18.4 GB · 11 files
$ fw verify ./DeepSeek-R1-Distill-Qwen-32B-4bit mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit.json --dir ./DeepSeek-R1-Distill-Qwen-32B-4bit
$ python3 fw.py verify ./DeepSeek-R1-Distill-Qwen-32B-4bit ./mlx-community__DeepSeek-R1-Distill-Qwen-32B-4bit.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit --revision 4e0d3848a0ad8f9fb54638891e4928f04fcca978 --local-dir ./DeepSeek-R1-Distill-Qwen-32B-4bittransformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit", revision="4e0d3848a0ad8f9fb54638891e4928f04fcca978")
model = AutoModelForCausalLM.from_pretrained("mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit", revision="4e0d3848a0ad8f9fb54638891e4928f04fcca978", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit --revision 4e0d3848a0ad8f9fb54638891e4928f04fcca978License Name MIT License Id MIT Class Permissive Redistribution yes Listing Hosted (signed) Decided Inherited from the base model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B: the strictest license along the lineage applies. 2026-11-14 Text in README.md Text sha256 d07ed184a2a36eb3164422a69e5d71749c8818d62168346fcce5c0ee7702e320 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: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.deepseekSubject: DeepSeek-R1-Distill-Qwen-32B-4bit Date: 2026-11-14Commit: 4e0d384Signed: 2DC28CC7B26A283B ✓ How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit.json.minisig
$ minisign -Vm DeepSeek-R1-Distill-Qwen-32B-4bit.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 No model in the catalog names this one as its parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bitOpen in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
412M params 1.65 GB deepseek_vit_412m.deepseek_v4_1_flash safetensors permissive Facts Params 412M Size 1.65 GB Formats safetensors Task image feature extraction License MIT permissive flip From: timm <huggingface.co/timm> Subject: deepseek_vit_412m.deepseek_v4_1_flash deepseek 8.03 TB deepseek-ai_DeepSeek-R1-0528-GGUF gguf permissive Facts Params not stated Size 8.03 TB Formats gguf Task text generation License MIT permissive flip From: bartowski <huggingface.co/bartowski> Subject: deepseek-ai_DeepSeek-R1-0528-GGUF deepseek 130 GB deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF gguf permissive Facts Params not stated Size 130 GB Formats gguf Task text generation License MIT permissive flip From: bartowski <huggingface.co/bartowski> Subject: deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF deepseek 8.29 TB deepseek-ai_DeepSeek-V3-0324-GGUF gguf permissive Facts Params not stated Size 8.29 TB Formats gguf Task text generation License MIT permissive flip From: bartowski <huggingface.co/bartowski> Subject: deepseek-ai_DeepSeek-V3-0324-GGUF deepseek 7.57 TB deepseek-ai_DeepSeek-V3.1-GGUF gguf permissive Facts Params not stated Size 7.57 TB Formats gguf Task text generation License MIT permissive flip From: bartowski <huggingface.co/bartowski> Subject: deepseek-ai_DeepSeek-V3.1-GGUF 284.3B params 302 GB deepseek-ai-DeepSeek-V4-Flash-8bit safetensors permissive Facts Params 284.3B Size 302 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/mlx-community> Subject: deepseek-ai-DeepSeek-V4-Flash-8bit
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.deepseekSubject: 
