- Size
- 125B parameters, 10.0B 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
- 24 Feb 2026the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen3_5MoeForConditionalGeneration
- On Hugging Face
- Qwen/Qwen3.5-122B-A10B738k downloads in the last 30 days, 658 likes
Scores
- effort none17.0%±3.827 Aug 2026, log
Epoch's name: qwen3.5-122b-a10b. Best closed model on this set: gpt-6.2-astra_max, 95.0% (OpenAI). All 148 results
- effort none0.9%via Epoch AI
Epoch's name: qwen3.5-122b-a10b. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- effort none84.3%conceptualreasoning.ai
Epoch's name: qwen3.5-122b-a10b. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results
- effort none32.2%27.6 to 36.8conceptualreasoning.ai
Epoch's name: qwen3.5-122b-a10b. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 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: 0.19 GB, worked out from the model's config (Qwen/Qwen3.5-122B-A10B), 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/Qwen3.5-122B-A10B-GGUF (converted by unsloth), 97k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-F16.gguf (0.85 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| UD-IQ3_XXS | 41.7 GBfile size | 42.4 GB41.7 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-IQ3_XXSOllama ollama run hf.co/unsloth/Qwen3.5-122B-A10B-GGUF:UD-IQ3_XXSDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Qwen3.5-122B-A10B-UD-IQ3_XXS.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| UD-IQ3_S | 43.4 GBfile size | 44.0 GB43.4 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-IQ3_SOllama ollama run hf.co/unsloth/Qwen3.5-122B-A10B-GGUF:UD-IQ3_SDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Qwen3.5-122B-A10B-UD-IQ3_S.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| Q3_K_S | 48.9 GBfile size, 3 parts | 49.6 GB48.9 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q3_K_SDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Q3_K_S/Qwen3.5-122B-A10B-Q3_K_S-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| Q3_K_M | 52.5 GBfile size, 3 parts | 53.2 GB52.5 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q3_K_MDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Q3_K_M/Qwen3.5-122B-A10B-Q3_K_M-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| UD-Q3_K_XL | 53.1 GBfile size, 3 parts | 53.7 GB53.1 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-Q3_K_XLDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "UD-Q3_K_XL/Qwen3.5-122B-A10B-UD-Q3_K_XL-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| UD-IQ4_XS | 56.1 GBfile size, 3 parts | 56.8 GB56.1 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-IQ4_XSDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "UD-IQ4_XS/Qwen3.5-122B-A10B-UD-IQ4_XS-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| UD-IQ4_NL | 57.2 GBfile size, 3 parts | 57.9 GB57.2 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-IQ4_NLDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "UD-IQ4_NL/Qwen3.5-122B-A10B-UD-IQ4_NL-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| Q4_K_S | 66.8 GBfile size, 3 parts | 67.5 GB66.8 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q4_K_SDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Q4_K_S/Qwen3.5-122B-A10B-Q4_K_S-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| MXFP4_MOE | 69.5 GBfile size, 3 parts | 70.2 GB69.5 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:MXFP4_MOEDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "MXFP4_MOE/Qwen3.5-122B-A10B-MXFP4_MOE-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| Q4_K_M | 71.3 GBfile size, 3 parts | 72.0 GB71.3 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q4_K_MDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Q4_K_M/Qwen3.5-122B-A10B-Q4_K_M-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| UD-Q4_K_XL | 71.7 GBfile size, 3 parts | 72.4 GB71.7 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-Q4_K_XLDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "UD-Q4_K_XL/Qwen3.5-122B-A10B-UD-Q4_K_XL-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| Q5_K_S | 80.5 GBfile size, 3 parts | 81.1 GB80.5 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q5_K_SDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Q5_K_S/Qwen3.5-122B-A10B-Q5_K_S-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| Q5_K_M | 85.2 GBfile size, 3 parts | 85.9 GB85.2 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q5_K_MDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Q5_K_M/Qwen3.5-122B-A10B-Q5_K_M-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| UD-Q5_K_XL | 85.6 GBfile size, 3 parts | 86.3 GB85.6 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-Q5_K_XLDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "UD-Q5_K_XL/Qwen3.5-122B-A10B-UD-Q5_K_XL-*-of-00003.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| Q6_K | 94.1 GBfile size, 4 parts | 94.8 GB94.1 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q6_KDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Q6_K/Qwen3.5-122B-A10B-Q6_K-*-of-00004.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| UD-Q6_K_XL | 104.7 GBfile size, 4 parts | 105.4 GB104.7 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-Q6_K_XLDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "UD-Q6_K_XL/Qwen3.5-122B-A10B-UD-Q6_K_XL-*-of-00004.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| Q8_0 | 121.0 GBfile size, 4 parts | 121.6 GB121.0 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:Q8_0Download hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "Q8_0/Qwen3.5-122B-A10B-Q8_0-*-of-00004.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| UD-Q8_K_XL | 159.1 GBfile size, 5 parts | 159.8 GB159.1 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:UD-Q8_K_XLDownload hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "UD-Q8_K_XL/Qwen3.5-122B-A10B-UD-Q8_K_XL-*-of-00005.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
| BF16 | 227.5 GBfile size, 5 parts | 228.2 GB227.5 + 0.19 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3.5-122B-A10B-GGUF:BF16Download hf download unsloth/Qwen3.5-122B-A10B-GGUF --include "BF16/Qwen3.5-122B-A10B-BF16-*-of-00005.gguf" --local-dir Qwen3.5-122B-A10B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLXbaa-ai/Qwen3.5-122B-A10B-RAM-48GB-MLX | 43.9 GBfile size | 44.6 GB43.9 + 0.19 + 0.50 | Download page |
| MLXmlx-community/Qwen3.5-122B-A10B-mxfp8 | 118.1 GBfile size | 118.8 GB118.1 + 0.19 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 233.0 GBfile size | 233.7 GB233.0 + 0.19 + 0.50 |
hf download Qwen/Qwen3.5-122B-A10B --local-dir Qwen3.5-122B-A10BOther conversions (17; sizes not read)
- Qwen/Qwen3.5-122B-A10B-GPTQ-Int4 GPTQ, int4, by the maker, 355k downloads
- Qwen/Qwen3.5-122B-A10B-FP8 FP8, by the maker, 123k downloads
- nvidia/Qwen3.5-122B-A10B-NVFP4 NVFP4, 47k downloads
- Intel/Qwen3.5-122B-A10B-int4-AutoRound Other, int4, 7.5k downloads
- RedHatAI/Qwen3.5-122B-A10B-NVFP4 NVFP4, 2.2k downloads
- QuantTrio/Qwen3.5-122B-A10B-AWQ AWQ, 1.7k downloads
- Sehyo/Qwen3.5-122B-A10B-NVFP4 NVFP4, 1.1k downloads
- scottgl/Qwen3.5-122B-A10B-NVFP4-GB10 NVFP4, 1.0k downloads
- cyankiwi/Qwen3.5-122B-A10B-AWQ-4bit AWQ, 4bit, 1.0k downloads
- RedHatAI/Qwen3.5-122B-A10B-FP8-dynamic FP8, 509 downloads
- taobao-mnn/Qwen3.5-122B-A10B-MNN Other, 503 downloads
- axteam/Qwen3.5-122B-A10B-FP8-dynamic FP8, 318 downloads
- axteam/Qwen3.5-122B-A10B-AWQ-4bit AWQ, 4bit, 304 downloads
- nota-ai/Qwen3.5-122B-A10B-NotaCompression-INT4 Other, int4, 303 downloads
- axteam/Qwen3.5-122B-A10B-AWQ-8bit AWQ, 8bit, 294 downloads
- litert-community/Qwen3.5-122B-A10B Other, 206 downloads
- shieldstar/Qwen3.5-122B-A10B-int4-AutoRound-EC GPTQ, int4, 198 downloads
The Hub tags 100 or more 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 |
|---|---|---|---|---|---|---|---|---|---|
| SiliconFlow | $0.26 | $2.08 | 256k | fp8 | 47 | 1.9 s | 99.9% | no | yes |
| deepinfra | $0.29 | $2.40 | 256k | not given | 25 | 0.4 s | ? | yes | yes |
| Novita | $0.40 | $3.20 | 256k | bf16 | 70 | 1.8 s | 100.0% | yes | no |
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/Qwen3.5-122B-A10B:siliconflow", "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.