Qwen3.5 35B A3B
Alibaba · Qwen/Qwen3.5-35B-A3B
Q4 file 22.0 GB (Q4_K_M) · runs well from 32 GB · Weights license: Apache 2.0
Quality
- LMArena · text · rating
- 1,394 ± 4Confidence interval 1,390–1,398 · 30,443 votes · rank 172 of the releaseLMArena 2026-10-22 · CC BY 4.0
No result in LiveBench 2026-06-25 Not in LiveBench 2026-06-25
Reported by the publisher
- MMLU-Pro
- 85.3Language
- MMLU-Redux
- 93.3Language
- C-Eval
- 90.2Language
- SuperGPQA
- 63.4Language
- IFEval
- 91.9Language
- IFBench
- 70.2Language
- MultiChallenge
- 60.0Language
- AA-LCR
- 58.5Language
Every reported result
- LongBench v2
- 59.0Language
- HLE w/ CoT
- 22.4Language
- GPQA Diamond
- 84.2Language
- HMMT Feb 25
- 89.0Language
- HMMT Nov 25
- 89.2Language
- SWE-bench Verified
- 69.2Language
- Terminal Bench 2
- 40.5Language
- LiveCodeBench v6
- 74.6Language
- CodeForces
- 2,028Language
- OJBench
- 36.0Language
- FullStackBench en
- 58.1Language
- FullStackBench zh
- 55.0Language
- BFCL-V4
- 67.3Language
- TAU2-Bench
- 81.2Language
- VITA-Bench
- 31.9Language
- DeepPlanning
- 22.8Language
- HLE w/ tool
- 47.4Language
- Browsecomp
- 61.0Language
- Browsecomp-zh
- 69.5Language
- WideSearch
- 57.1Language
- Seal-0
- 41.4Language
- MMMLU
- 85.2Language
- MMLU-ProX
- 81.0Language
- NOVA-63
- 57.1Language
- INCLUDE
- 79.7Language
- Global PIQA
- 86.6Language
- PolyMATH
- 64.4Language
- WMT24++
- 76.3Language
- MAXIFE
- 86.6Language
- MMMU
- 81.4Vision Language
- MMMU-Pro
- 75.1Vision Language
- MathVision
- 83.9Vision Language
- Mathvista (mini)
- 86.2Vision Language
- DynaMath
- 85.0Vision Language
- ZEROBench
- 8Vision Language
- ZEROBench_sub
- 34.1Vision Language
- VlmsAreBlind
- 97.0Vision Language
- RealWorldQA
- 84.1Vision Language
- MMStar
- 81.9Vision Language
- MMBench EN-DEV-v1.1
- 91.5Vision Language
- SimpleVQA
- 58.3Vision Language
- HallusionBench
- 67.9Vision Language
- OmniDocBench1.5
- 89.3Vision Language
- CharXiv (RQ)
- 77.5Vision Language
- MMLongBench-Doc
- 59.5Vision Language
- CC-OCR
- 80.7Vision Language
- AI2D_TEST
- 92.6Vision Language
- OCRBench
- 91.0Vision Language
- ERQA
- 64.8Vision Language
- CountBench
- 97.8Vision Language
- RefCOCO (avg)
- 89.2Vision Language
- ODInW13
- 42.6Vision Language
- EmbSpatialBench
- 83.1Vision Language
- RefSpatialBench
- 63.5Vision Language
- LingoQA
- 79.2Vision Language
- Hypersim
- 13.1Vision Language
- SUNRGBD
- 33.4Vision Language
- Nuscene
- 14.6Vision Language
- VideoMME (w sub.)
- 86.6Vision Language
- VideoMME (w/o sub.)
- 82.5Vision Language
- VideoMMMU
- 80.4Vision Language
- MLVU
- 85.6Vision Language
- MVBench
- 74.8Vision Language
- LVBench
- 71.4Vision Language
- MMVU
- 72.3Vision Language
- ScreenSpot Pro
- 68.6Vision Language
- OSWorld-Verified
- 54.5Vision Language
- AndroidWorld
- 71.1Vision Language
- SLAKE
- 78.7Vision Language
- PMC-VQA
- 62.0Vision Language
- MedXpertQA-MM
- 61.4Vision Language
Across Qwen3.5 sizes
| Benchmark (publisher settings) | 9B | 35B A3B |
|---|---|---|
| MMLU-Pro | 82.5 | 85.3 |
| MMLU-Redux | 91.1 | 93.3 |
| C-Eval | 88.2 | 90.2 |
| SuperGPQA | 58.2 | 63.4 |
| IFEval | 91.5 | 91.9 |
| IFBench | 64.5 | 70.2 |
| MultiChallenge | 54.5 | 60.0 |
| AA-LCR | 63.0 | 58.5 |
| LongBench v2 | 55.2 | 59.0 |
| GPQA Diamond | 81.7 | 84.2 |
| HMMT Feb 25 | 83.2 | 89.0 |
| HMMT Nov 25 | 82.9 | 89.2 |
| LiveCodeBench v6 | 65.6 | 74.6 |
| OJBench | 29.2 | 36.0 |
| BFCL-V4 | 66.1 | 67.3 |
| TAU2-Bench | 79.1 | 81.2 |
| VITA-Bench | 29.8 | 31.9 |
| DeepPlanning | 18.0 | 22.8 |
| MMMLU | 81.2 | 85.2 |
| MMLU-ProX | 76.3 | 81.0 |
| NOVA-63 | 55.9 | 57.1 |
| INCLUDE | 75.6 | 79.7 |
| Global PIQA | 83.2 | 86.6 |
| PolyMATH | 57.3 | 64.4 |
| WMT24++ | 72.6 | 76.3 |
| MAXIFE | 83.4 | 86.6 |
| MMMU | 78.4 | 81.4 |
| MMMU-Pro | 70.1 | 75.1 |
| MathVision | 78.9 | 83.9 |
| Mathvista (mini) | 85.7 | 86.2 |
| DynaMath | 83.6 | 85.0 |
| ZEROBench | 3.0 | 8 |
| ZEROBench_sub | 31.1 | 34.1 |
| VlmsAreBlind | 93.7 | 97.0 |
| RealWorldQA | 80.3 | 84.1 |
| MMStar | 79.7 | 81.9 |
| MMBench EN-DEV-v1.1 | 90.1 | 91.5 |
| SimpleVQA | 51.2 | 58.3 |
| HallusionBench | 69.3 | 67.9 |
| OmniDocBench1.5 | 87.7 | 89.3 |
| CharXiv (RQ) | 73.0 | 77.5 |
| MMLongBench-Doc | 57.7 | 59.5 |
| CC-OCR | 79.3 | 80.7 |
| AI2D_TEST | 90.2 | 92.6 |
| OCRBench | 89.2 | 91.0 |
| ERQA | 55.5 | 64.8 |
| CountBench | 97.2 | 97.8 |
| RefCOCO (avg) | 89.7 | 89.2 |
| EmbSpatialBench | 83.0 | 83.1 |
| RefSpatialBench | 58.5 | 63.5 |
| LingoQA | 80.4 | 79.2 |
| Hypersim | 13.5 | 13.1 |
| Nuscene | 11.8 | 14.6 |
| VideoMME (w sub.) | 84.5 | 86.6 |
| VideoMME (w/o sub.) | 78.4 | 82.5 |
| VideoMMMU | 78.9 | 80.4 |
| MLVU | 84.4 | 85.6 |
| MVBench | 74.4 | 74.8 |
| LVBench | 70.0 | 71.4 |
| MMVU | 67.8 | 72.3 |
| ScreenSpot Pro | 65.2 | 68.6 |
| OSWorld-Verified | 41.8 | 54.5 |
| AndroidWorld | 57.8 | 71.1 |
| SLAKE | 79.0 | 78.7 |
| PMC-VQA | 57.9 | 62.0 |
| MedXpertQA-MM | 49.9 | 61.4 |
Values as printed on the card, with the publisher's own settings (card section: Benchmark Results › Language; Benchmark Results › Vision Language); column “Qwen3.5-35B-A3B”. Not comparable across publishers and not used in any ranking. Model card
Run it
Run it
File Q4_K_M · 22 GB · unsloth/Qwen3.5-35B-A3B-GGUF · What is Q4?
Measured 63.1 tok/s · MXFP4 · 1 machine · 2 sources · all rows
ollama run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M- Install Ollama
- Run the command above
- Ask:
Explain what a context window is, in two sentences.
Runs on
Fast memory holds it 33
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 33
Within memory, outside the fast part 50
Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.
Show all 50
One memory tier short 9
The same machines with the next memory size up would hold it in fast memory.
Show all 9
Qwen3.5 35B A3B is a text model from Alibaba with 35B parameters, 3B of them active per token (mixture of experts). It was released on February 24, 2026 and reads up to 262,144 tokens of context. Its Q4 weights plus working room come to about 27 GB before the machine's reserve; the smallest reference machines whose fast memory holds that are Mac mini M5 Pro · 64 GB unified (~35 GB with its reserve) and RTX 5090 · 32 GB VRAM (~29 GB with its reserve). We collected 27 downloadable GGUF and MLX files from 2 publisher sources; the most downloaded GGUF source is unsloth's (5.5M downloads on the Hub). It has no result in LiveBench 2026-06-25. Its LMArena text rating is 1,394 ± 4 (release 2026-10-22), a separate human-preference scale.
Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.
On the reference machines
| Where Q4 sits | ||||
|---|---|---|---|---|
| Mac mini M2 · 8 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~29 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac mini M4 · 16 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~31 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac mini M4 · 24 GB unifiedLarger than its memoryNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~33 GB | Larger than its memory | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| Mac mini M4 · 32 GB unifiedLarger than its memoryUD-IQ4_XS131,072 tokens | ~35 GB | Larger than its memory | UD-IQ4_XS | 131,072 tokens |
| Mac mini M5 Pro · 64 GB unifiedFast memory holds itQ8_0131,072 tokens | ~35 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| Mac Studio M5 Max · 128 GB unifiedFast memory holds itQ8_0262,144 tokens | ~35 GB | Fast memory holds it | Q8_0 | 262,144 tokens |
| Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itQ8_0262,144 tokens | ~35 GB | Fast memory holds it | Q8_0 | 262,144 tokens |
| RTX 4060 · 8 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~29 GB | In memory, outside the fast part | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| RTX 3060 · 12 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~29 GB | In memory, outside the fast part | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| RTX 5080 · 16 GB VRAMIn memory, outside the fast partNo file on the site's quant ladder fits the fast memory at 8,192 tokensNo file in the previous column | ~29 GB | In memory, outside the fast part | No file on the site's quant ladder fits the fast memory at 8,192 tokens | No file in the previous column |
| RTX 4090 · 24 GB VRAMIn memory, outside the fast partUD-IQ4_XS32,768 tokens | ~29 GB | In memory, outside the fast part | UD-IQ4_XS | 32,768 tokens |
| RTX 5090 · 32 GB VRAMFast memory holds itQ4_K_M131,072 tokens | ~29 GB | Fast memory holds it | Q4_K_M | 131,072 tokens |
| DGX H100 · 8 × 80 GBFast memory holds itQ8_0262,144 tokens | ~43 GB | Fast memory holds it | Q8_0 | 262,144 tokens |
The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.
Compare it with the dense Qwen 27B checkpoint for coding; the published MoE design activates about 3B language parameters per token.
Active parameters are not the weights to store. The full 35B weight count matters to the generic memory plan.
Versions to download
Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth (5.5M Hub downloads), at Q4_K_M. On a Mac it opens on the most downloaded MLX source. Sizes are the Hub's published bytes. What is Q4?
unsloth · 5.5M downloads
unsloth/Qwen3.5-35B-A3B-GGUF · Qwen3.5-35B-A3B-Q4_K_M.gguf · 22.0 GB
Run this file
ollama run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_Mllama-server -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_Mlms get https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF- mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac
Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)
Fine-tunes, adapters and other versions
- Quantized versions
- 310
- Fine-tunes
- 186
- Adapters · merges
- 48 · 8
Browse them on the Hugging Face model tree · read 2026-10-23
Uncensored and abliterated versions
Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.
114 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).
Measured speed
Tokens per second by machine
Output tok/s · 2 machines · every row in the table · What is a token?
| DGX Spark | 63.13 | MXFP4 (MoE; 35B total / 3B active) | llama.cpp CUDA (SM121a, source build) | Qwen3.5-35B-A3B MXFP4 GGUF (the source names neither the repository nor the file) |
|---|---|---|---|---|
| MacBook Air 13-inch M5 32GB | 55.0 | 2-bit oQ2 (group size 64), MLX safetensors | oMLX (MLX) with native/lightning MTP speculative decoding, TurboQuant KV cache enabled, max 4 concurrent requests | mlx-works/Qwen3.5-35B-A3B-oQ2-mtp (third-party 2-bit MLX conversion with embedded MTP) |
| MacBook Air 13-inch M5 32GB | 55.0 | 3-bit oQ3 (group size 64), MLX safetensors | oMLX (MLX) with native/lightning MTP speculative decoding, TurboQuant KV cache enabled, max 4 concurrent requests | mlx-works/Qwen3.5-35B-A3B-oQ3-mtp (third-party 3-bit MLX conversion with embedded MTP) |
Sources: nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark · mlx-works model card (Hugging Face) · third-party quantization · mlx-works model card (Hugging Face) · third-party quantization · not estimated
How to run
~27 GB of Q4 weights plus working room, before the machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.
Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
vllm serve Qwen/Qwen3.5-35B-A3B --port 8000 --tensor-parallel-size 8 --max-model-len 262144 --reasoning-parser qwen3 python -m sglang.launch_server --model-path Qwen/Qwen3.5-35B-A3B --port 8000 --tp-size 8 --mem-fraction-static 0.8 --context-length 262144 --reasoning-parser qwen3transformers serve --force-model Qwen/Qwen3.5-35B-A3B --port 8000 --continuous-batchingEvidence level: Generic estimate only; no execution reproduced by this site.
- Publisher sampling defaults
- temperature 1 · top_p 0.95 · top_k 20generation_config.json · read 2026-10-23source
- Chat template markers
- tool calls · thinkingmarkers found in the template, not a test of the feature · read 2026-10-23source
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- Qwen/Qwen3.5-35B-A3B
- Task and modality
- language and reasoning · text + image + video
- Count and basis
- 35B · language component · 3B active
- Context
- 262,144 tokens published for this model
- Architecture
- MoE
- Released
- QwenLM Qwen GitHub README (News) · read 2026-10-13source
- Runtime and precision
- No local execution verified.
- Languages
- 201 languages Publisher's statement · read 2026-10-18source
- Commercial use
- Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Every stored field
- Revision checked
- 59d61f3ce65a6d9863b86d2e96597125219dc754
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Library
- transformers
- Hub task tag
- image-text-to-text
- Declared base models
- Qwen/Qwen3.5-35B-A3B-Base
- Formats
- transformers, safetensors
- Access
- Open download
- Publisher kind
- Official
- Repository created
- 2026-02-24creation is not the model's release
- Repository updated
- 2026-04-24a commit is not a release date
- Hub downloads (30 days) · likes
- 1,476,096 · 1,546this repository only · read 2026-10-25
- Catalog state
- Hub config or weights found; no inventory benchmark link
The MoE activates about 3B language parameters per token, but all 35B weights still matter for storage and the generic memory estimate.
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · LiveBench 2026-06-25 overall
Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-09-26.

























































