- Size
- 235B parameters, 22.0B active (from the repo name)counted from the safetensors header on the Hub
- Licence
- custom, read it, Apache License 2.0Our reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 21 Jul 2025the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen3MoeForCausalLM
- On Hugging Face
- Qwen/Qwen3-235B-A22B-Instruct-250754k downloads in the last 30 days, 813 likes
Scores
- Edit format: diff59.6%9 May 2025, aider.chat
Epoch's name: Qwen3-235B-A22B-Instruct-2507. Best closed model on this set: gpt-5-2025-08-07_high, 88.0% (OpenAI). All 72 results
- default setting11.0%via Epoch AI
Epoch's name: Qwen3-235B-A22B-Instruct-2507. Best closed model on this set: claude-fable-5_max, 98.5% (Anthropic). All 318 results
- default setting1.3%via Epoch AI
Epoch's name: Qwen3-235B-A22B-Instruct-2507. Best closed model on this set: gpt-6-astra_max, 95.0% (OpenAI). All 299 results
- default setting78.4%conceptualreasoning.ai
Epoch's name: Qwen3-235B-A22B-Instruct-2507. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- default setting52.9%Fiction.live leaderboard
Epoch's name: parasail-qwen3-235b-a22b-instruct-2507. Best closed model on this set: gpt-5-2025-08-07_medium, 97.2% (OpenAI). All 61 results
- default setting23.5%18.7 to 28.4conceptualreasoning.ai
Epoch's name: Qwen3-235B-A22B-Instruct-2507. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results
- default setting38.7%WeirdML Leaderboard
Epoch's name: Qwen3-235B-A22B-Instruct-2507. Best closed model on this set: gpt-6-astra_promax, 93.6% (OpenAI). All 173 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.5 GB, worked out from the model's config (Qwen/Qwen3-235B-A22B-Instruct-2507), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF (converted by unsloth), 38k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q3_K_S | 94.5 GBfile size, 3 parts | 96.4 GB94.5 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q3_K_SDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q3_K_S/Qwen3-235B-A22B-Instruct-2507-Q3_K_S-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| UD-Q3_K_XL | 97.0 GBfile size, 3 parts | 99.0 GB97.0 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:UD-Q3_K_XLDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "UD-Q3_K_XL/Qwen3-235B-A22B-Instruct-2507-UD-Q3_K_XL-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q3_K_M | 104.7 GBfile size, 3 parts | 106.7 GB104.7 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q3_K_MDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q3_K_M/Qwen3-235B-A22B-Instruct-2507-Q3_K_M-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| IQ4_XS | 116.9 GBfile size, 3 parts | 118.8 GB116.9 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:IQ4_XSDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "IQ4_XS/Qwen3-235B-A22B-Instruct-2507-IQ4_XS-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q4_0 | 124.0 GBfile size, 3 parts | 126.0 GB124.0 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q4_0Download hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q4_0/Qwen3-235B-A22B-Instruct-2507-Q4_0-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q4_K_S | 124.5 GBfile size, 3 parts | 126.5 GB124.5 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q4_K_SDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q4_K_S/Qwen3-235B-A22B-Instruct-2507-Q4_K_S-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| UD-Q4_K_XL | 125.1 GBfile size, 3 parts | 127.1 GB125.1 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:UD-Q4_K_XLDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "UD-Q4_K_XL/Qwen3-235B-A22B-Instruct-2507-UD-Q4_K_XL-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q4_K_M | 132.4 GBfile size, 3 parts | 134.4 GB132.4 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q4_K_MDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q4_K_M/Qwen3-235B-A22B-Instruct-2507-Q4_K_M-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q4_1 | 137.1 GBfile size, 3 parts | 139.1 GB137.1 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q4_1Download hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q4_1/Qwen3-235B-A22B-Instruct-2507-Q4_1-*-of-00003.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q5_K_S | 150.8 GBfile size, 4 parts | 152.7 GB150.8 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q5_K_SDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q5_K_S/Qwen3-235B-A22B-Instruct-2507-Q5_K_S-*-of-00004.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q5_K_M | 155.4 GBfile size, 4 parts | 157.3 GB155.4 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q5_K_MDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q5_K_M/Qwen3-235B-A22B-Instruct-2507-Q5_K_M-*-of-00004.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| UD-Q5_K_XL | 157.3 GBfile size, 4 parts | 159.3 GB157.3 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:UD-Q5_K_XLDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "UD-Q5_K_XL/Qwen3-235B-A22B-Instruct-2507-UD-Q5_K_XL-*-of-00004.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q6_K | 179.8 GBfile size, 4 parts | 181.7 GB179.8 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q6_KDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q6_K/Qwen3-235B-A22B-Instruct-2507-Q6_K-*-of-00004.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| UD-Q6_K_XL | 188.1 GBfile size, 5 parts | 190.1 GB188.1 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:UD-Q6_K_XLDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "UD-Q6_K_XL/Qwen3-235B-A22B-Instruct-2507-UD-Q6_K_XL-*-of-00005.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| Q8_0 | 232.8 GBfile size, 6 parts | 234.7 GB232.8 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:Q8_0Download hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "Q8_0/Qwen3-235B-A22B-Instruct-2507-Q8_0-*-of-00006.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| UD-Q8_K_XL | 255.4 GBfile size, 6 parts | 257.4 GB255.4 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:UD-Q8_K_XLDownload hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "UD-Q8_K_XL/Qwen3-235B-A22B-Instruct-2507-UD-Q8_K_XL-*-of-00006.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
| BF16 | 438.0 GBfile size, 10 parts | 440.0 GB438.0 + 1.5 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF:BF16Download hf download unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF --include "BF16/Qwen3-235B-A22B-Instruct-2507-BF16-*-of-00010.gguf" --local-dir Qwen3-235B-A22B-Instruct-2507-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitlmstudio-community/Qwen3-235B-A22B-Instruct-2507-MLX-4bit | 123.2 GBfile size | 125.1 GB123.2 + 1.5 + 0.50 | Download page |
| MLX 8bitlmstudio-community/Qwen3-235B-A22B-Instruct-2507-MLX-8bit | 232.6 GBfile size | 234.6 GB232.6 + 1.5 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 437.9 GBfile size | 439.9 GB437.9 + 1.5 + 0.50 |
hf download Qwen/Qwen3-235B-A22B-Instruct-2507 --local-dir Qwen3-235B-A22B-Instruct-2507Other conversions (17; sizes not read)
- Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 FP8, by the maker, 19k downloads
- QuantTrio/Qwen3-235B-A22B-Instruct-2507-AWQ AWQ, 3.6k downloads
- intel-ai/Qwen3-235B-A22B-Instruct-2507-MXFP4 Other, mxfp4, 1.6k downloads
- amd/Qwen3-235B-A22B-Instruct-2507-MXFP4 Other, mxfp4, 1.3k downloads
- nvidia/Qwen3-235B-A22B-Instruct-2507-NVFP4 NVFP4, 1.3k downloads
- RedHatAI/Qwen3-235B-A22B-Instruct-2507-NVFP4 NVFP4, 733 downloads
- zjiayu064/Qwen3-235B-A22B-Instruct-2507-BitsMoE-1.6bit Other, 6bit, 271 downloads
- chriswritescode/Qwen3-235B-A22B-Instruct-2507-INT4-W4A16 Other, int4, 162 downloads
- 0x3/Qwen3-235B-A22B-Instruct-2507-AWQ AWQ, 77 downloads
- QuantTrio/Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4-Int8Mix GPTQ, int4, 58 downloads
- amanwalksdownthestreet/Qwen3-235B-A22B-Instruct-2507-exl3 EXL3, 31 downloads
- NVFP4/Qwen3-235B-A22B-Instruct-2507-FP4 NVFP4, 23 downloads
- NeuroSenko/Qwen3-235B-A22B-Instruct-2507-exl3 EXL3, 23 downloads
- bullerwins/Qwen3-235B-A22B-Instruct-2507-exl3-5.0bpw EXL3, 15 downloads
- AIDXteam/Qwen3-235B-A22B-Instruct-2507-AWQ AWQ, 13 downloads
- Doctor-Shotgun/Qwen3-235B-A22B-Instruct-2507-exl3_3.07bpw-h6-custom EXL3, 12 downloads
- chriswritescode/Qwen3-235B-A22B-Instruct-2507-AWQ-Swift AWQ, 11 downloads
The Hub tags 74 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
3 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| DeepInfra | $0.09 | $0.55 | 256k | fp8 | 31 | 0.4 s | 96.6% | yes | yes |
| Venice | $0.15 | $0.75 | 125k | fp8 | 34 | 0.5 s | 99.4% | yes | yes |
| Parasail | $0.14 | $0.80 | 128k | fp8 | 34 | 0.5 s | 99.2% | yes | yes |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "Qwen/Qwen3-235B-A22B-Instruct-2507:deepinfra", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.