- Size
- 4.0B 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
- 5 Aug 2025the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen3ForCausalLM
- On Hugging Face
- Qwen/Qwen3-4B-Instruct-25072.7M downloads in the last 30 days, 1.1k likes
Scores
- default setting45.8%±2.928 Aug 2026, log
Epoch's name: qwen3-4b-instruct-2507. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results
- default setting52.2%±6.628 Aug 2026, log
Epoch's name: qwen3-4b-instruct-2507. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 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: 1.1 GB, worked out from the model's config (Qwen/Qwen3-4B-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/Qwen3-4B-Instruct-2507-GGUF (converted by unsloth), 904k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| UD-IQ3_XXS | 1.6 GBfile size | 3.2 GB1.6 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-IQ3_XXSOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-IQ3_XXSDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-IQ3_XXS.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q3_K_S | 1.8 GBfile size | 3.4 GB1.8 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q3_K_SOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q3_K_SDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q3_K_S.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q3_K_M | 1.9 GBfile size | 3.6 GB1.9 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q3_K_MOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q3_K_MDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q3_K_M.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| UD-Q3_K_XL | 2.0 GBfile size | 3.6 GB2.0 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q3_K_XLOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q3_K_XLDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q3_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| IQ4_XS | 2.1 GBfile size | 3.7 GB2.1 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:IQ4_XSOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:IQ4_XSDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-IQ4_XS.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q4_0 | 2.2 GBfile size | 3.8 GB2.2 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_0Ollama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_0Download hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q4_0.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| IQ4_NL | 2.2 GBfile size | 3.8 GB2.2 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:IQ4_NLOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:IQ4_NLDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-IQ4_NL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q4_K_S | 2.2 GBfile size | 3.8 GB2.2 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_SOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_SDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q4_K_S.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q4_K_M | 2.3 GBfile size | 4.0 GB2.3 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_MOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_MDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q4_K_M.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| UD-Q4_K_XL | 2.4 GBfile size | 4.0 GB2.4 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q4_K_XLOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q4_K_XLDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q4_1 | 2.4 GBfile size | 4.0 GB2.4 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_1Ollama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_1Download hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q4_1.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q5_K_S | 2.6 GBfile size | 4.3 GB2.6 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q5_K_SOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q5_K_SDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q5_K_S.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q5_K_M | 2.7 GBfile size | 4.3 GB2.7 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q5_K_MOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q5_K_MDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q5_K_M.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| UD-Q5_K_XL | 2.7 GBfile size | 4.3 GB2.7 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q5_K_XLOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q5_K_XLDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q5_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q6_K | 3.1 GBfile size | 4.7 GB3.1 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q6_KOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q6_KDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q6_K.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| UD-Q6_K_XL | 3.4 GBfile size | 5.0 GB3.4 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q6_K_XLOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q6_K_XLDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q6_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| Q8_0 | 4.0 GBfile size | 5.6 GB4.0 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q8_0Ollama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q8_0Download hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q8_0.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| UD-Q8_K_XL | 4.7 GBfile size | 6.3 GB4.7 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q8_K_XLOllama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q8_K_XLDownload hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q8_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
| F16 | 7.5 GBfile size | 9.1 GB7.5 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:F16Ollama ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:F16Download hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-F16.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitmlx-community/Qwen3-4B-Instruct-2507-4bit | 2.1 GBfile size | 3.7 GB2.1 + 1.1 + 0.50 | Download page |
| MLX 4bitlmstudio-community/Qwen3-4B-Instruct-2507-MLX-4bit | 2.1 GBfile size | 3.7 GB2.1 + 1.1 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 7.5 GBfile size | 9.1 GB7.5 + 1.1 + 0.50 |
hf download Qwen/Qwen3-4B-Instruct-2507 --local-dir Qwen3-4B-Instruct-2507Other conversions (16; sizes not read)
- Qwen/Qwen3-4B-Instruct-2507-FP8 FP8, by the maker, 1.6M downloads
- unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit bitsandbytes, 4bit, 110k downloads
- llmat/Qwen3-4B-Instruct-2507-NVFP4 NVFP4, 77k downloads
- unsloth/Qwen3-4B-Instruct-2507-bnb-4bit bitsandbytes, 4bit, 12k downloads
- warshanks/Qwen3-4B-Instruct-2507-AWQ AWQ, 5.3k downloads
- litert-community/Qwen3-4B-Instruct-2507 Other, 2.7k downloads
- cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit AWQ, 4bit, 2.3k downloads
- JunHowie/Qwen3-4B-Instruct-2507-GPTQ-Int8 GPTQ, int8, 2.3k downloads
- RedHatAI/Qwen3-4B-Instruct-2507-quantized.w4a16 Other, w4a16, 1.4k downloads
- Eslzzyl/Qwen3-4B-Instruct-2507-AWQ AWQ, 1.0k downloads
- experimentalmachines/Qwen3-4B-Instruct-2507-ExecuTorch Other, 962 downloads
- JunHowie/Qwen3-4B-Instruct-2507-GPTQ-Int4 GPTQ, int4, 935 downloads
- RedHatAI/Qwen3-4B-Instruct-2507-quantized.w8a8 Other, w8a8, 763 downloads
- Firworks/Qwen3-4B-Instruct-2507-nvfp4 NVFP4, 541 downloads
- superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 GPTQ, int4, 530 downloads
- vllm-project/Qwen3-4B-Instruct-2507-GPTQ-Int4 GPTQ, int4, 168 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
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
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- llamafactory/tiny-random-qwen32M94kUnreviewed
- unsloth/Qwen3-4B-Instruct-25074.0B38kUnreviewed
- allenai/Molmo2-4B4.9B33kUnreviewed
- nvidia/Nemotron-Research-GooseReason-4B-Instruct4.4B2.6kUnreviewed
- nvidia/Privasis-Cleaner-4B4.0B2.3kUnreviewed
- allenai/intent-aware-lfqa-qwen3-4b-intent-explicit2.2kUnreviewed
- tencent/TCAndon-Router4.0B2.0kUnreviewed
- apple/SimpleSD-4B-instruct4.0B661Unreviewed
- allenai/intent-aware-lfqa-qwen3-4b-baseline238Unreviewed
- allenai/intent-aware-lfqa-qwen3-4b-intent-implicit232Unreviewed
- allenai/intent-aware-lfqa-qwen3-4b-multiview227Unreviewed
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.