alt.freeweights.qwen / Qwen3.5-122B-A10B-NVFP4

From:

unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-122B-A10B-NVFP4

Date: 2026-11-15Commit: 0a6419dSigned: 2DC28CC7B26A283B ✓

Image text to text model with 75.2B parameters. Safetensors weights, 79.1 GB in all. Published by unsloth under Apache-2.0.

75.2B params

79.1GBQwen3.5-122B-A10B-NVFP4safetensorspermissive

FactsParams75.2BSize79.1 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive

$ fw get unsloth/Qwen3.5-122B-A10B-NVFP4
# manifest sha256 63bb2c89810e… · 79.1 GB · 18 files
$ fw verify ./Qwen3.5-122B-A10B-NVFP4 unsloth/Qwen3.5-122B-A10B-NVFP4

From sourceHosted (signed)unsloth/Qwen3.5-122B-A10B-NVFP4Last check: 2026-11-15 05:09 UTC

Run at home Get help

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

Quantized of Qwen3.5-122B-A10B.

Works with

Run23 Fine-tune29 Convert15 Evaluate13 Scan13 Apps62

Runs with

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

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 23

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 79.1 GB
Weights: 79.0 GB (safetensors)
Parameters: 75.2B
Formats: safetensors
Task: image text to text
License: Apache-2.0 (permissive)
Files: 18, each with a sha256
Publisher: unsloth
Added: 2026-11-15
Section: alt.freeweights.qwen

Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.5-122B-A10B

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
From source	huggingface.co	2026-11-15 05:09 UTC	passed

Model card

From the publisher at commit 0a6419d. Shown as plain text with links; images open at the publisher.

Read our How to Run NVFP4 quants Guide!#

See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks.

https://github.com/unslothai/unsloth/ https://discord.gg/unsloth https://unsloth.ai/docs/models/qwen3.6

Run in vLLM#

uv venv unsloth-nvfp4-env --python 3.13
source unsloth-nvfp4-env/bin/activate
uv pip install "vllm>=0.25.0" "flashinfer-python>=0.6.13" "nvidia-cutlass-dsl>=4.5.2" --torch-backend=auto

vllm serve unsloth/Qwen3.5-122B-A10B-NVFP4 \
    --speculative-config '{"method": "mtp", "num_speculative_tokens": 2}'

Do not use the Marlin backend (around 2x slower); let vLLM auto-select the NVFP4 kernel.

Qwen3.5-122B-A10B#

Image: image

Qwen Chat

Note. This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.

These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.

Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.

Qwen3.5 Highlights#

Qwen3.5 features the following enhancement:

Unified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
Efficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
Scalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.
Global Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.
Next-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.

Image: Benchmark Results

For more details, please refer to our blog post Qwen3.5.

Model Overview#

Type: Causal Language Model with Vision Encoder
Training Stage: Pre-training & Post-training
Language Model
- Number of Parameters: 122B in total and 10B activated
- Hidden Dimension: 3072
- Token Embedding: 248320 (Padded)
- Number of Layers: 48
- Hidden Layout: 16 × (3 × (Gated DeltaNet → MoE) → 1 × (Gated Attention → MoE))
- Gated DeltaNet:
  - Number of Linear Attention Heads: 64 for V and 16 for QK
  - Head Dimension: 128
- Gated Attention:
  - Number of Attention Heads: 32 for Q and 2 for KV
  - Head Dimension: 256
  - Rotary Position Embedding Dimension: 64
- Mixture Of Experts
  - Number of Experts: 256
  - Number of Activated Experts: 8 Routed + 1 Shared
  - Expert Intermediate Dimension: 1024
- LM Output: 248320 (Padded)
- MTP: trained with multi-steps
Context Length: 262,144 natively and extensible up to 1,010,000 tokens.

Benchmark Results#

Language#

| Knowledge

| MMLU-Pro | 83.7 | 80.8 | 84.4 | 86.7 | 86.1 | 85.3

| MMLU-Redux | 93.7 | 91.0 | 93.8 | 94.0 | 93.2 | 93.3

| C-Eval | 82.2 | 76.2 | 92.1 | 91.9 | 90.5 | 90.2

| SuperGPQA | 58.6 | 54.6 | 64.9 | 67.1 | 65.6 | 63.4

| Instruction Following

| IFEval | 93.9 | 88.9 | 87.8 | 93.4 | 95.0 | 91.9

| IFBench | 75.4 | 69.0 | 51.7 | 76.1 | 76.5 | 70.2

| MultiChallenge | 59.0 | 45.3 | 50.2 | 61.5 | 60.8 | 60.0

| Long Context

| AA-LCR | 68.0 | 50.7 | 60.0 | 66.9 | 66.1 | 58.5

| LongBench v2 | 56.8 | 48.2 | 54.8 | 60.2 | 60.6 | 59.0

| STEM & Reasoning

| HLE w/ CoT | 19.4 | 14.9 | 18.2 | 25.3 | 24.3 | 22.4

| GPQA Diamond | 82.8 | 80.1 | 81.1 | 86.6 | 85.5 | 84.2

| HMMT Feb 25 | 89.2 | 90.0 | 85.1 | 91.4 | 92.0 | 89.0

| HMMT Nov 25 | 84.2 | 90.0 | 89.5 | 90.3 | 89.8 | 89.2

| Coding

| SWE-bench Verified | 72.0 | 62.0 | -- | 72.0 | 72.4 | 69.2

| Terminal Bench 2 | 31.9 | 18.7 | -- | 49.4 | 41.6 | 40.5

| LiveCodeBench v6 | 80.5 | 82.7 | 75.1 | 78.9 | 80.7 | 74.6

| CodeForces | 2160 | 2157 | 2146 | 2100 | 1899 | 2028

| OJBench | 40.4 | 41.5 | 32.7 | 39.5 | 40.1 | 36.0

| FullStackBench en | 30.6 | 58.9 | 61.1 | 62.6 | 60.1 | 58.1

| FullStackBench zh | 35.2 | 60.4 | 63.1 | 58.7 | 57.4 | 55.0

| General Agent

| BFCL-V4 | 55.5 | -- | 54.8 | 72.2 | 68.5 | 67.3

| TAU2-Bench | 69.8 | -- | 58.5 | 79.5 | 79.0 | 81.2

| VITA-Bench | 13.9 | -- | 31.6 | 33.6 | 41.9 | 31.9

| DeepPlanning | 17.9 | -- | 17.1 | 24.1 | 22.6 | 22.8

| Search Agent

| HLE w/ tool | 35.8 | 19.0 | -- | 47.5 | 48.5 | 47.4

| Browsecomp | 48.1 | 41.1 | -- | 63.8 | 61.0 | 61.0

| Browsecomp-zh | 49.5 | 42.9 | -- | 69.9 | 62.1 | 69.5

| WideSearch | 47.2 | 40.4 | -- | 60.5 | 61.1 | 57.1

| Seal-0 | 34.2 | 45.1 | -- | 44.1 | 47.2 | 41.4

| Multilingualism

| MMMLU | 86.2 | 78.2 | 83.4 | 86.7 | 85.9 | 85.2

| MMLU-ProX | 78.5 | 74.5 | 77.9 | 82.2 | 82.2 | 81.0

| NOVA-63 | 51.9 | 51.1 | 55.4 | 58.6 | 58.1 | 57.1

| INCLUDE | 81.8 | 74.0 | 81.0 | 82.8 | 81.6 | 79.7

| Global PIQA | 88.5 | 84.1 | 85.7 | 88.4 | 87.5 | 86.6

| PolyMATH | 67.3 | 54.0 | 60.1 | 68.9 | 71.2 | 64.4

| WMT24++ | 80.7 | 74.4 | 75.8 | 78.3 | 77.6 | 76.3

| MAXIFE | 85.3 | 83.7 | 83.2 | 87.9 | 88.0 | 86.6

CodeForces: evaluated on our own query set.
TAU2-Bench: we follow the official setup except for the airline domain, where all models are evaluated by applying the fixes proposed in the Claude Opus 4.5 system card.
Search Agent: most search agents built on our model adopt a simple context-folding strategy(256k): once the cumulative Tool Response length reaches a preset threshold, earlier Tool Responses are pruned from the history to keep the context within limits.
WideSearch: we use a 256k context window without any context management.
MMLU-ProX: we report the averaged accuracy on 29 languages.
WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL.
MAXIFE: we report the accuracy on English + multilingual original prompts (totally 23 settings).
Empty cells (--) indicate scores not yet available or not applicable.

Vision Language#

| STEM and Puzzle

| MMMU | 79.0 | 79.6 | 80.6 | 83.9 | 82.3 | 81.4

| MMMU-Pro | 67.3 | 68.4 | 69.3 | 76.9 | 75.0 | 75.1

| MathVision | 71.9 | 71.1 | 74.6 | 86.2 | 86.0 | 83.9

| Mathvista(mini) | 79.1 | 79.8 | 85.8 | 87.4 | 87.8 | 86.2

| DynaMath | 81.4 | 78.8 | 82.8 | 85.9 | 87.7 | 85.0

| ZEROBench | 3 | 4 | 4 | 9 | 10 | 8

| ZEROBench_sub | 27.3 | 26.3 | 28.4 | 36.2 | 36.2 | 34.1

| VlmsAreBlind | 75.8 | 85.5 | 79.5 | 96.7 | 96.9 | 97.0

| BabyVision | 20.9 | 18.6 | 22.2 | 40.2 / 34.5 | 44.6 / 34.8 | 38.4 / 29.6

| General VQA

| RealWorldQA | 79.0 | 70.3 | 81.3 | 85.1 | 83.7 | 84.1

| MMStar | 74.1 | 73.8 | 78.7 | 82.9 | 81.0 | 81.9

| MMBenchEN-DEV-v1.1 | 86.8 | 88.3 | 89.7 | 92.8 | 92.6 | 91.5

| SimpleVQA | 56.8 | 57.6 | 61.3 | 61.7 | 56.0 | 58.3

| HallusionBench | 63.2 | 59.9 | 66.7 | 67.6 | 70.0 | 67.9

| Text Recognition and Document Understanding

| OmniDocBench1.5 | 77.0 | 85.8 | 84.5 | 89.8 | 88.9 | 89.3

| CharXiv(RQ) | 68.6 | 67.2 | 66.1 | 77.2 | 79.5 | 77.5

| MMLongBench-Doc | 50.3 | -- | 56.2 | 59.0 | 60.2 | 59.5

| CC-OCR | 70.8 | 68.1 | 81.5 | 81.8 | 81.0 | 80.7

| AI2D_TEST | 88.2 | 87.0 | 89.2 | 93.3 | 92.9 | 92.6

| OCRBench | 82.1 | 76.6 | 87.5 | 92.1 | 89.4 | 91.0

| Spatial Intelligence

| ERQA | 54.0 | 45.0 | 52.5 | 62.0 | 60.5 | 64.8

| CountBench | 91.0 | 90.0 | 93.7 | 97.0 | 97.8 | 97.8

| RefCOCO(avg) | -- | -- | 91.1 | 91.3 | 90.9 | 89.2

| ODInW13 | -- | -- | 43.2 | 44.5 | 41.1 | 42.6

| EmbSpatialBench | 80.7 | 71.8 | 84.3 | 83.9 | 84.5 | 83.1

| RefSpatialBench | 9.0 | 2.2 | 69.9 | 69.3 | 67.7 | 63.5

| LingoQA | 62.4 | 12.8 | 66.8 | 80.8 | 82.0 | 79.2

| Hypersim | -- | -- | 11.0 | 12.7 | 13.0 | 13.1

| SUNRGBD | -- | -- | 34.9 | 36.2 | 35.4 | 33.4

| Nuscene | -- | -- | 13.9 | 15.4 | 15.2 | 14.6

| Video Understanding

The publisher's README is longer; it is cut here. Read the rest at the source.

Files

18 files · 79.1 GBWeights 79.0 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 18 files with their sha256

File	Size	sha256
.gitattributes	1.64 KB	fe81d528e7ee055bbcf6a310afe0f2808423a4a16d45225f29c285926abef08d
README.md	94.0 KB	7191dd82e9b892f51d469a9fd19849b40f2bdc397e3134ff3de66cb74c4029d0
added_tokens.json	904 B	e5f9bfb644ead13bd36dd6cfc41553a93b7c264c0a2e1ac67d033aa8250c8538
chat_template.jinja	7.99 KB	8452ca85cb1e0ff04304c02f417a53305d5ba17f6eb9d5693343ad8355f985a8
config.json	25.1 KB	7412be6f2448a6bab7948ed331392b6b6dc8c221ddc938fff7a91a704892ac20
generation_config.json	214 B	7a62af64a07e5c0b76492811a53ead5c27b1e75e3489568217edd87626976b33
model-00001-of-00002.safetensors	50.0 GB	8e80ac73d8e7f3093127ddc28ddb1e2f9a3cda32b632adf562e74fc4ff85f1d6
model-00002-of-00002.safetensors	24.0 GB	60492b95087b955316e5ef2f91a4abcacc8b316f17c8f6803699fe2986736b21
model.safetensors.index.json	17.0 MB	c58669788fb944ceac1dd47362e0290e15e92a89579a101067bd6ca4b1944662
model_mtp.safetensors	5.05 GB	b4fc887d1af4d780a74f4e06298b660bd96b4e431d483f04de1cfeb4df9ecc2c
preprocessor_config.json	781 B	b99182e09450f26453502b3c3390cce36b33dc8c4a1f3ee21807762e168c74ab
processor_config.json	1.30 KB	01562eddd6f9e9ec4bc31656a3b7055284cafbf889acc6c4348dca431ae31f68
recipe.yaml	838 B	f20972a2ee6becc97740bc6bcb97cf60a7f1afef67ad63f08b172610b3612be6
special_tokens_map.json	876 B	ce5cbe737f4aacc7696180aac743091101b59e4dc5a338d9fc8a6f716aa513f7
tokenizer.json	20.0 MB	1a6329cee073f44581f13a111a96addf12a9d9a65b2ac6f81fa441ec1b63f5c9
tokenizer_config.json	1.19 KB	bfd46bda4ad4feb24dc16fd7a0780bcfdf6a93e8ebb9a712b9657ddc4aba6a46
video_preprocessor_config.json	817 B	59c5c9eb52182eb14c06ffb10ca9effd29adce5f238a95de23ca14a38dbd2cb1
vocab.json	5.23 MB	4ab0d5c096294054b66444a116a20baf6e29998fc1fae410ffe4b6fadbc56b5c

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
0a6419df60 pinned now	2026-11-15 05:09 UTC	18 files · 79.1 GB

Use it

$ fw get unsloth/Qwen3.5-122B-A10B-NVFP4
# manifest sha256 63bb2c89810e… · 79.1 GB · 18 files
$ fw verify ./Qwen3.5-122B-A10B-NVFP4 unsloth/Qwen3.5-122B-A10B-NVFP4

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/Qwen3.5-122B-A10B-NVFP4.json --dir ./Qwen3.5-122B-A10B-NVFP4
$ python3 fw.py verify ./Qwen3.5-122B-A10B-NVFP4 ./unsloth__Qwen3.5-122B-A10B-NVFP4.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/Qwen3.5-122B-A10B-NVFP4 --revision 0a6419df6090328f1f08d863a4587f583241e13c --local-dir ./Qwen3.5-122B-A10B-NVFP4

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForImageTextToText, AutoProcessor
processor = AutoProcessor.from_pretrained("unsloth/Qwen3.5-122B-A10B-NVFP4", revision="0a6419df6090328f1f08d863a4587f583241e13c")
model = AutoModelForImageTextToText.from_pretrained("unsloth/Qwen3.5-122B-A10B-NVFP4", revision="0a6419df6090328f1f08d863a4587f583241e13c", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve unsloth/Qwen3.5-122B-A10B-NVFP4 --revision 0a6419df6090328f1f08d863a4587f583241e13c

Run at home

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: 7191dd82e9b892f51d469a9fd19849b40f2bdc397e3134ff3de66cb74c4029d0
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:

unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.qwenSubject: Qwen3.5-122B-A10B-NVFP4Date: 2026-11-15Commit: 0a6419dSigned: 2DC28CC7B26A283B ✓

Upstream: unsloth/Qwen3.5-122B-A10B-NVFP4
Pinned commit: 0a6419df6090328f1f08d863a4587f583241e13c
Manifest: Qwen3.5-122B-A10B-NVFP4.json · .minisig
Manifest sha256: 63bb2c89810ee1f37f655830a707eb147dabf9bafc327af1d7dcb71717d8c54c
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:09 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/unsloth/Qwen3.5-122B-A10B-NVFP4.json
$ curl -O https://freeweights.allternit.com/manifests/unsloth/Qwen3.5-122B-A10B-NVFP4.json.minisig
$ minisign -Vm Qwen3.5-122B-A10B-NVFP4.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

Qwen/Qwen3.5-122B-A10B · 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 unsloth/Qwen3.5-122B-A10B-NVFP4

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. Qwen3.5-122B-A10B-NVFP4.json. Provenance. Takedown history: none.

Source

huggingface.co/unsloth/Qwen3.5-122B-A10B-NVFP4

Related models

All of alt.freeweights.qwen →

From:

BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen

From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1

From:

BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923

From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct

From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA

From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF

Qwen3.5-122B-A10B-NVFP4

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

Read our How to Run NVFP4 quants Guide!#

Run in vLLM#

Qwen3.5-122B-A10B#

Qwen3.5 Highlights#

Model Overview#

Benchmark Results#

Language#

Vision Language#

Files

Use it

License

Provenance

How to verify

Model tree

Related models