Qwen3-Omni-30B-A3B-Instruct
Runs on your machine
Choose a machine
We then show the largest format that fits, from real file sizes where we have them.
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
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.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.0 GB, a rough allowance by model size, because we do not have this model's attention config. Choose a machine above to see a verdict for each format. Method
weights context cache runtime
GGUF for llama.cpp, Ollama, LM Studio and others
ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF (converted by ggml-org), 122k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| Q4_K_M | 17.3 GBfile size | 19.8 GB17.3 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF:Q4_K_MOllama ollama run hf.co/ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF:Q4_K_MDownload hf download ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF --include "Qwen3-Omni-30B-A3B-Instruct-Q4_K_M.gguf" --local-dir Qwen3-Omni-30B-A3B-Instruct-GGUF | |
| Q8_0 | 30.3 GBfile size | 32.8 GB30.3 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF:Q8_0Ollama ollama run hf.co/ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF:Q8_0Download hf download ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF --include "Qwen3-Omni-30B-A3B-Instruct-Q8_0.gguf" --local-dir Qwen3-Omni-30B-A3B-Instruct-GGUF | |
| BF16 | 56.9 GBfile size | 59.4 GB56.9 + 2.0 + 0.50 | Commandsllama.cpp llama-server -hf ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF:BF16Ollama ollama run hf.co/ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF:BF16Download hf download ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF --include "Qwen3-Omni-30B-A3B-Instruct-bf16.gguf" --local-dir Qwen3-Omni-30B-A3B-Instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| MLX mxfp4abnormalmapstudio/Qwen3-Omni-30B-A3B-Instruct-mxfp4-mlx | 15.1 GBfile size | 17.6 GB15.1 + 2.0 + 0.50 | Download page | |
| MLX 4bitpherber3/Qwen3-Omni-30B-A3B-Instruct-4bit-mlx | 16.0 GBfile size | 18.5 GB16.0 + 2.0 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 65.7 GBfile size | 68.2 GB65.7 + 2.0 + 0.50 |
hf download Qwen/Qwen3-Omni-30B-A3B-Instruct --local-dir Qwen3-Omni-30B-A3B-InstructOther conversions (8; sizes not read)
- cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit AWQ, 4bit, 80k downloads
- Intel/Qwen3-Omni-30B-A3B-Instruct-int4-AutoRound Other, int4, 1.9k downloads
- cyankiwi/Qwen3-Omni-30B-A3B-Instruct-AWQ-8bit AWQ, 8bit, 1.4k downloads
- catplusplus/Qwen3-Omni-30B-A3B-Instruct-NVFP4 NVFP4, 360 downloads
- YihongJin/Qwen3-Omni-30B-A3B-Instruct-NVFP4-W4A16-awq AWQ, nvfp4, 102 downloads
- yemara/Qwen3-Omni-30B-A3B-Instruct-NVFP4 NVFP4, 58 downloads
- lainlives/Qwen3-Omni-30B-A3B-Instruct-bnb-4bit bitsandbytes, 4bit, 49 downloads
- hemilu223/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit AWQ, 4bit, 43 downloads
The Hub tags 39 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
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.
Fine-tunes of this model
- Cloudflare/clef-omni35.3B10kUnreviewed
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, 15:15 UTC. The repo. Found a mistake on this page? Tell us.