- Size
- 79.7B parameterscounted 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
- 30 Jan 2026the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen3NextForCausalLM
- On Hugging Face
- Qwen/Qwen3-Coder-Next337k downloads in the last 30 days, 1.7k likes
Scores
- default setting0.0%via Epoch AI
Epoch's name: qwen3-coder-next. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- default setting34.4%±0.0WeirdML Leaderboard, via Epoch AI
Epoch's name: qwen3-coder-next. 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: 0.75 GB, worked out from the model's config (Qwen/Qwen3-Coder-Next), 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-Coder-Next-GGUF (converted by unsloth), 201k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| UD-IQ3_XXS | 26.5 GBfile size | 27.8 GB26.5 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-IQ3_XXSOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-IQ3_XXSDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-IQ3_XXS.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-IQ3_S | 27.7 GBfile size | 28.9 GB27.7 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-IQ3_SOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-IQ3_SDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-IQ3_S.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q3_K_S | 31.0 GBfile size | 32.3 GB31.0 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q3_K_SOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q3_K_SDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-Q3_K_S.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q3_K_S | 32.2 GBfile size | 33.5 GB32.2 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q3_K_SOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:Q3_K_SDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-Q3_K_S.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q3_K_M | 33.5 GBfile size | 34.7 GB33.5 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q3_K_MOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q3_K_MDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-Q3_K_M.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q3_K_XL | 33.8 GBfile size | 35.0 GB33.8 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q3_K_XLOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q3_K_XLDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-Q3_K_XL.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q3_K_M | 35.7 GBfile size | 36.9 GB35.7 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q3_K_MOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:Q3_K_MDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-Q3_K_M.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-IQ4_XS | 35.8 GBfile size | 37.0 GB35.8 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-IQ4_XSOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-IQ4_XSDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-IQ4_XS.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-IQ4_NL | 36.5 GBfile size | 37.8 GB36.5 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-IQ4_NLOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-IQ4_NLDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-IQ4_NL.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| IQ4_XS | 39.7 GBfile size | 41.0 GB39.7 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:IQ4_XSOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:IQ4_XSDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-IQ4_XS.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| IQ4_NL | 42.0 GBfile size | 43.3 GB42.0 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:IQ4_NLOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:IQ4_NLDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-IQ4_NL.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q4_0 | 42.2 GBfile size | 43.5 GB42.2 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_0Ollama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:Q4_0Download hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-Q4_0.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q4_K_S | 42.4 GBfile size | 43.7 GB42.4 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_K_SOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:Q4_K_SDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-Q4_K_S.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q4_K_S | 42.9 GBfile size | 44.2 GB42.9 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_SOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_SDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-Q4_K_S.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| MXFP4_MOE | 44.7 GBfile size | 46.0 GB44.7 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:MXFP4_MOEOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:MXFP4_MOEDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-MXFP4_MOE.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q4_K_M | 45.2 GBfile size | 46.4 GB45.2 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_K_MOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:Q4_K_MDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-Q4_K_M.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q4_K_M | 45.9 GBfile size | 47.2 GB45.9 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_MOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_MDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-Q4_K_M.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q4_K_XL | 46.2 GBfile size | 47.5 GB46.2 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_XLOllama ollama run hf.co/unsloth/Qwen3-Coder-Next-GGUF:UD-Q4_K_XLDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Qwen3-Coder-Next-UD-Q4_K_XL.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q4_1 | 46.6 GBfile size, 3 parts | 47.9 GB46.6 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_1Download hf download unsloth/Qwen3-Coder-Next-GGUF --include "Q4_1/Qwen3-Coder-Next-Q4_1-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q5_K_S | 51.3 GBfile size, 3 parts | 52.5 GB51.3 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q5_K_SDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Q5_K_S/Qwen3-Coder-Next-Q5_K_S-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q5_K_S | 52.0 GBfile size, 3 parts | 53.2 GB52.0 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q5_K_SDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "UD-Q5_K_S/Qwen3-Coder-Next-UD-Q5_K_S-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q5_K_M | 52.9 GBfile size, 3 parts | 54.2 GB52.9 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q5_K_MDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Q5_K_M/Qwen3-Coder-Next-Q5_K_M-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q5_K_M | 55.2 GBfile size, 3 parts | 56.4 GB55.2 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q5_K_MDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "UD-Q5_K_M/Qwen3-Coder-Next-UD-Q5_K_M-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q5_K_XL | 55.5 GBfile size, 3 parts | 56.7 GB55.5 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q5_K_XLDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "UD-Q5_K_XL/Qwen3-Coder-Next-UD-Q5_K_XL-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q6_K | 61.1 GBfile size, 3 parts | 62.4 GB61.1 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q6_KDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "Q6_K/Qwen3-Coder-Next-Q6_K-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q6_K | 61.3 GBfile size, 3 parts | 62.5 GB61.3 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q6_KDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "UD-Q6_K/Qwen3-Coder-Next-UD-Q6_K-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q6_K_XL | 68.1 GBfile size, 3 parts | 69.3 GB68.1 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q6_K_XLDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "UD-Q6_K_XL/Qwen3-Coder-Next-UD-Q6_K_XL-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| Q8_0 | 79.0 GBfile size, 3 parts | 80.2 GB79.0 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:Q8_0Download hf download unsloth/Qwen3-Coder-Next-GGUF --include "Q8_0/Qwen3-Coder-Next-Q8_0-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| UD-Q8_K_XL | 80.4 GBfile size, 3 parts | 81.7 GB80.4 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:UD-Q8_K_XLDownload hf download unsloth/Qwen3-Coder-Next-GGUF --include "UD-Q8_K_XL/Qwen3-Coder-Next-UD-Q8_K_XL-*-of-00003.gguf" --local-dir Qwen3-Coder-Next-GGUF |
| BF16 | 148.5 GBfile size, 4 parts | 149.8 GB148.5 + 0.75 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-Coder-Next-GGUF:BF16Download hf download unsloth/Qwen3-Coder-Next-GGUF --include "BF16/Qwen3-Coder-Next-BF16-*-of-00004.gguf" --local-dir Qwen3-Coder-Next-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 8bitNexVeridian/Qwen3-Coder-Next-8bit | 78.8 GBfile size | 80.1 GB78.8 + 0.75 + 0.50 | Download page |
| MLX 8bitlmstudio-community/Qwen3-Coder-Next-MLX-8bit | 78.8 GBfile size | 80.1 GB78.8 + 0.75 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 148.4 GBfile size | 149.7 GB148.4 + 0.75 + 0.50 |
hf download Qwen/Qwen3-Coder-Next --local-dir Qwen3-Coder-NextOther conversions (19; sizes not read)
- Qwen/Qwen3-Coder-Next-FP8 FP8, by the maker, 120k downloads
- RedHatAI/Qwen3-Coder-Next-FP8-dynamic FP8, 30k downloads
- qtum/Qwen3-Coder-Next-AWQ AWQ, 11k downloads
- cyankiwi/Qwen3-Coder-Next-AWQ-4bit AWQ, 4bit, 4.3k downloads
- GadflyII/Qwen3-Coder-Next-NVFP4 NVFP4, 3.8k downloads
- RedHatAI/Qwen3-Coder-Next-NVFP4 NVFP4, 2.2k downloads
- bullpoint/Qwen3-Coder-Next-AWQ-4bit AWQ, 4bit, 1.9k downloads
- Intel/Qwen3-Coder-Next-int4-AutoRound Other, int4, 1.8k downloads
- unsloth/Qwen3-Coder-Next-FP8 FP8, 1.1k downloads
- btbtyler09/Qwen3-Coder-Next-GPTQ-4bit GPTQ, 4bit, 788 downloads
- unsloth/Qwen3-Coder-Next-FP8-Dynamic FP8, 777 downloads
- defnoteatin/PseudoBrain-Qwen3-Coder-Next-NVFP4 NVFP4, 629 downloads
- thousandml/Qwen3-Coder-Next-CQ-4bit Other, 4bit, 614 downloads
- defnoteatin/PseudoBrain-Qwen3-Coder-Next-W4A16 Other, w4a16, 594 downloads
- saricles/Qwen3-Coder-Next-NVFP4-GB10 NVFP4, 359 downloads
- cyankiwi/Qwen3-Coder-Next-AWQ-8bit AWQ, 8bit, 343 downloads
- inference-optimization/Qwen3-Coder-Next.w4a16 Other, w4a16, 282 downloads
- 6block/Qwen3-Coder-Next-GPTQ GPTQ, 182 downloads
- dazipe/Qwen3-Coder-Next-GPTQ-Int4A16 GPTQ, 52 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
2 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 |
|---|---|---|---|---|---|---|---|---|---|
| Parasail | $0.12 | $0.80 | 256k | bf16 | 73 | 0.6 s | 100.0% | yes | yes |
| featherless-ai | ? | ? | ? | not given | ? | ? | ? | not given | not given |
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-Coder-Next:parasail", "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.