CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.5-35B-A3B-FP8
From: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-35B-A3B-FP8

Date: 2026-11-15Commit: 9d1823dSigned: 2DC28CC7B26A283B ✓

Image text to text model with 36B parameters. Safetensors weights, 37.5 GB in all. Published by Qwen under Apache-2.0.

36B params37.5GBQwen3.5-35B-A3B-FP8safetensorspermissive
FactsParams36BSize37.5 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get Qwen/Qwen3.5-35B-A3B-FP8
# manifest sha256 f23b7d68258d… · 37.5 GB · 28 files
$ fw verify ./Qwen3.5-35B-A3B-FP8 Qwen/Qwen3.5-35B-A3B-FP8
From sourceHosted (signed)Qwen/Qwen3.5-35B-A3B-FP8Last check: 2026-11-15 04:34 UTC
Run at homeGet help

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

Quantized of Qwen3.5-35B-A3B.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
37.5 GB
Weights
37.5 GB (safetensors)
Parameters
36B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
28, each with a sha256
Publisher
Qwen
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.5-35B-A3B

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 04:34 UTCpassed

Model card

From the publisher at commit 9d1823d. Shown as plain text with links; images open at the publisher.

Qwen3.5-35B-A3B-FP8#

Image: image

Qwen Chat

Note. This repository contains FP8-quantized 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.

The quantization method is fine-grained fp8 quantization with block size of 128, and its performance metrics are nearly identical to those of the original model.

Tip. For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Alibaba Cloud Model Studio.

In particular, Qwen3.5-Flash is the hosted version corresponding to Qwen3.5-35B-A3B with more production features, e.g., 1M context length by default and official built-in tools. For more information, please refer to the User Guide.

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: 35B in total and 3B activated
    • Hidden Dimension: 2048
    • Token Embedding: 248320 (Padded)
    • Number of Layers: 40
    • Hidden Layout: 10 × (3 × (Gated DeltaNet → MoE) → 1 × (Gated Attention → MoE))
    • Gated DeltaNet:
      • Number of Linear Attention Heads: 32 for V and 16 for QK
      • Head Dimension: 128
    • Gated Attention:
      • Number of Attention Heads: 16 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: 512
    • 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#

| | GPT-5-mini 2025-08-07 | GPT-OSS-120B | Qwen3-235B-A22B | Qwen3.5-122B-A10B | Qwen3.5-27B | Qwen3.5-35B-A3B

| 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#

| | GPT-5-mini 2025-08-07 | Claude-Sonnet-4.5 | Qwen3-VL-235B-A22B | Qwen3.5-122B-A10B | Qwen3.5-27B | Qwen3.5-35B-A3B

| 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

| VideoMME(w sub.) | 83.5 | 81.1 | 83.8 | 87.3 | 87.0

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

Files

28 files · 37.5 GBWeights 37.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 28 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE11.3 KB50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
README.md93.4 KB2e09fd9d54bd1854b1be9e161fe65002493e025812a2447399e8eeea6b90bbfc
chat_template.jinja7.76 KBa4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715
config.json20.5 KB236c373b0682a4f40c2fa49ef8e5f722a87a8dbfe265286b6d5260b23d7cb229
configuration.json51 B2d4464e2ead06bc9bc718c781309ad1e7baded626d66e8dcdc8b469ba185faf0
generation_config.json244 B4f25002776b741773666203dcea8f54619f177ace3ae483d311102092a4658e0
merges.txt3.35 MBa9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
model.safetensors-00001-of-00014.safetensors2.69 GB8eec0929a43c759abc4e230ca6c55b1a314f26b8870cb63941b674b95ce6d49e
model.safetensors-00002-of-00014.safetensors2.69 GB4cb364215f617628defac9a1345c9122ab65b36d555349285f73b7595eb068a6
model.safetensors-00003-of-00014.safetensors2.69 GBf94b20e10e856926b902a51c9aa575ff8beb483cef6130996e098a40e3a2a92a
model.safetensors-00004-of-00014.safetensors2.69 GBc3a0d1593280aeb44ba100a1dbef643071284519b58654b14591984ae558c5d3
model.safetensors-00005-of-00014.safetensors2.69 GBa754c48ee879302bbb16debedea9032010bb616aa3fe9f1fd0340f81230b5e12
model.safetensors-00006-of-00014.safetensors2.69 GBb5435e836f62b7d915e84f0f327d07ed773a0939d4acd3e16b9b082c35318ce9
model.safetensors-00007-of-00014.safetensors2.69 GB684840ee3af77f22ddaa5df7330384c472b7e50efdd4ba1699558152a182045c
model.safetensors-00008-of-00014.safetensors2.69 GB70ac96a66c7bc85d97649e460bdfaebc5947c191bb0742d596c35d53d833060a
model.safetensors-00009-of-00014.safetensors3.65 GB775cec9a6755ecddcd3d41954f14e40051a5d8306ce6d5f6ccd96af58a8d93cb
model.safetensors-00010-of-00014.safetensors2.69 GB5a86d13781bb91dbfce6602095e424f9b53fe76d3bb0d1ea1800f584fc1f41ab
model.safetensors-00011-of-00014.safetensors2.69 GB6f0c1b222c972fb8ce4936f861a71e6f2987db80b523d290954473d7643bf417
model.safetensors-00012-of-00014.safetensors2.69 GB040c27529a66e43f3a2cfef338ac121f5897ea476984ee3ba35540a49388809b
model.safetensors-00013-of-00014.safetensors3.01 GBee1088b806b0ce6ad374eec852503efa68d70f01480bd75815f8ca7b91327df0
model.safetensors-00014-of-00014.safetensors1.27 GB38842b8f3d0a4ea29c064317591c4b6529efbcc0a1f7665c41b58e6852638dc9
model.safetensors.index.json8.09 MBb009f7a49c442fce959a2ff6fee41c69248879b90d7ff5636ec6d2068ac4876d
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
tokenizer.json12.8 MB5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
tokenizer_config.json16.7 KB316230d6a809701f4db5ea8f8fc862bc3a6f3229c937c174e674ff3ca0a64ac8
video_preprocessor_config.json385 B7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
9d1823d2de pinned now2026-11-15 04:34 UTC28 files · 37.5 GB

Use it

$ fw get Qwen/Qwen3.5-35B-A3B-FP8
# manifest sha256 f23b7d68258d… · 37.5 GB · 28 files
$ fw verify ./Qwen3.5-35B-A3B-FP8 Qwen/Qwen3.5-35B-A3B-FP8
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-35B-A3B-FP8.json --dir ./Qwen3.5-35B-A3B-FP8 $ python3 fw.py verify ./Qwen3.5-35B-A3B-FP8 ./Qwen__Qwen3.5-35B-A3B-FP8.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen3.5-35B-A3B-FP8 --revision 9d1823d2dee688a6b25e77009dc727688c44936e --local-dir ./Qwen3.5-35B-A3B-FP8
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("Qwen/Qwen3.5-35B-A3B-FP8", revision="9d1823d2dee688a6b25e77009dc727688c44936e") model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3.5-35B-A3B-FP8", revision="9d1823d2dee688a6b25e77009dc727688c44936e", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve Qwen/Qwen3.5-35B-A3B-FP8 --revision 9d1823d2dee688a6b25e77009dc727688c44936e
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
LICENSE
Text sha256
50cbab8a892c5f2993b8c7351a99182507472def3b1374558308605d99b86b32
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: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject: Qwen3.5-35B-A3B-FP8Date: 2026-11-15Commit: 9d1823dSigned: 2DC28CC7B26A283B ✓
Upstream
Qwen/Qwen3.5-35B-A3B-FP8
Pinned commit
9d1823d2dee688a6b25e77009dc727688c44936e
Manifest
Qwen3.5-35B-A3B-FP8.json · .minisig
Manifest sha256
f23b7d68258d33e5667a4c699be8c66f06ff8f858de8d795ac449c2057413ded
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:34 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-35B-A3B-FP8.json $ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3.5-35B-A3B-FP8.json.minisig $ minisign -Vm Qwen3.5-35B-A3B-FP8.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/Qwen3.5-35B-A3B · 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 Qwen/Qwen3.5-35B-A3B-FP8
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.5-35B-A3B-FP8.json. Provenance. Takedown history: none.
Source
huggingface.co/Qwen/Qwen3.5-35B-A3B-FP8

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