- Size
- 4.0B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
- On the Hub since
- 28 Apr 2025the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen3ForCausalLM
- On Hugging Face
- Qwen/Qwen3-4B-Base414k downloads in the last 30 days, 119 likes
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: 1.1 GB, worked out from the model's config (Qwen/Qwen3-4B-Base), 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
mradermacher/Qwen3-4B-Base-GGUF (converted by mradermacher), 4.4k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 1.6 GBfile size | 3.2 GB1.6 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q2_KOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q2_KDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q2_K.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q3_K_S | 1.8 GBfile size | 3.4 GB1.8 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q3_K_SOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q3_K_SDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q3_K_S.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q3_K_M | 1.9 GBfile size | 3.6 GB1.9 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q3_K_MOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q3_K_MDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q3_K_M.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q3_K_L | 2.1 GBfile size | 3.7 GB2.1 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q3_K_LOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q3_K_LDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q3_K_L.gguf" --local-dir Qwen3-4B-Base-GGUF |
| IQ4_XS | 2.1 GBfile size | 3.8 GB2.1 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:IQ4_XSOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:IQ4_XSDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.IQ4_XS.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q4_K_S | 2.2 GBfile size | 3.8 GB2.2 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q4_K_SOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q4_K_SDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q4_K_S.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q4_K_M | 2.3 GBfile size | 4.0 GB2.3 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q4_K_MOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q4_K_MDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q4_K_M.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q5_K_S | 2.6 GBfile size | 4.3 GB2.6 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q5_K_SOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q5_K_SDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q5_K_S.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q5_K_M | 2.7 GBfile size | 4.3 GB2.7 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q5_K_MOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q5_K_MDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q5_K_M.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q6_K | 3.1 GBfile size | 4.7 GB3.1 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q6_KOllama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q6_KDownload hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q6_K.gguf" --local-dir Qwen3-4B-Base-GGUF |
| Q8_0 | 4.0 GBfile size | 5.6 GB4.0 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:Q8_0Ollama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:Q8_0Download hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.Q8_0.gguf" --local-dir Qwen3-4B-Base-GGUF |
| F16 | 7.5 GBfile size | 9.1 GB7.5 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-4B-Base-GGUF:F16Ollama ollama run hf.co/mradermacher/Qwen3-4B-Base-GGUF:F16Download hf download mradermacher/Qwen3-4B-Base-GGUF --include "Qwen3-4B-Base.f16.gguf" --local-dir Qwen3-4B-Base-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitjohnlakness/Qwen3-4B-Base-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-Base --local-dir Qwen3-4B-BaseOther conversions (8; sizes not read)
- unsloth/Qwen3-4B-Base-unsloth-bnb-4bit bitsandbytes, 4bit, 8.5k downloads
- unsloth/Qwen3-4B-Base-bnb-4bit bitsandbytes, 4bit, 1.8k downloads
- liodon-ai/Qwen3-4B-Base-ONNX Other, 347 downloads
- Xylolabs/Qwen3-4B-Base-Tenstorrent-Tensix-BFP4 Other, 83 downloads
- Xylolabs/Qwen3-4B-Base-Tenstorrent-Tensix-BFP8 Other, 76 downloads
- Sohailhosseini/Qwen3-4B-Base-FP8 FP8, 73 downloads
- wesjos/SFT-Qwen3-4B-Base-math bitsandbytes, 58 downloads
- mistralrs-community/Qwen3-4B-Base-UQFF Other, 19 downloads
The Hub tags 65 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.
- Qwen/Qwen3-4B4.0B3.1MReviewed
- unsloth/Qwen3-4B-Base4.0B16kUnreviewed
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.