- Size
- 596M 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/Qwen3-0.6B-Base525k downloads in the last 30 days, 227 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: 0.88 GB, worked out from the model's config (Qwen/Qwen3-0.6B-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/Qwen3-0.6B-Base-GGUF (converted by mradermacher), 6.1k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 0.28 GBfile size | 1.7 GB0.28 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q2_KOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q2_KDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q2_K.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q3_K_S | 0.30 GBfile size | 1.7 GB0.30 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q3_K_SOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q3_K_SDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q3_K_S.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q3_K_M | 0.32 GBfile size | 1.7 GB0.32 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q3_K_MOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q3_K_MDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q3_K_M.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q3_K_L | 0.34 GBfile size | 1.7 GB0.34 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q3_K_LOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q3_K_LDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q3_K_L.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| IQ4_XS | 0.34 GBfile size | 1.7 GB0.34 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:IQ4_XSOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:IQ4_XSDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.IQ4_XS.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q4_K_S | 0.36 GBfile size | 1.7 GB0.36 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q4_K_SOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q4_K_SDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q4_K_S.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q4_K_M | 0.37 GBfile size | 1.7 GB0.37 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q4_K_MOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q4_K_MDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q4_K_M.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q5_K_S | 0.41 GBfile size | 1.8 GB0.41 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q5_K_SOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q5_K_SDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q5_K_S.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q5_K_M | 0.41 GBfile size | 1.8 GB0.41 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q5_K_MOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q5_K_MDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q5_K_M.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q6_K | 0.46 GBfile size | 1.8 GB0.46 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q6_KOllama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q6_KDownload hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q6_K.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| Q8_0 | 0.60 GBfile size | 2.0 GB0.60 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:Q8_0Ollama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:Q8_0Download hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.Q8_0.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
| F16 | 1.1 GBfile size | 2.5 GB1.1 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3-0.6B-Base-GGUF:F16Ollama ollama run hf.co/mradermacher/Qwen3-0.6B-Base-GGUF:F16Download hf download mradermacher/Qwen3-0.6B-Base-GGUF --include "Qwen3-0.6B-Base.f16.gguf" --local-dir Qwen3-0.6B-Base-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitmlx-community/Qwen3-0.6B-Base-4bit | 0.31 GBfile size | 1.7 GB0.31 + 0.88 + 0.50 | Download page |
| MLX 8bitmlx-community/Qwen3-0.6B-Base-8bit | 0.59 GBfile size | 2.0 GB0.59 + 0.88 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 1.1 GBfile size | 2.5 GB1.1 + 0.88 + 0.50 |
hf download Qwen/Qwen3-0.6B-Base --local-dir Qwen3-0.6B-BaseOther conversions (9; sizes not read)
- unsloth/Qwen3-0.6B-Base-unsloth-bnb-4bit bitsandbytes, 4bit, 1.6k downloads
- unsloth/Qwen3-0.6B-Base-bnb-4bit bitsandbytes, 4bit, 331 downloads
- dqy08/Qwen3-0.6B-Base-ONNX Other, 86 downloads
- isogen/Qwen3-0.6B-Base-exl3-8bpw-h8 EXL3, 77 downloads
- liodon-ai/Qwen3-0.6B-Base-FP8 FP8, 51 downloads
- mingyi456/Qwen3-0.6B-Base-DF11 Other, 50 downloads
- mistralrs-community/Qwen3-0.6B-Base-UQFF Other, 37 downloads
- Jeney/Qwen3-0.6B-Base-bnb-4bit bitsandbytes, 4bit, 34 downloads
- liodon-ai/Qwen3-0.6B-Base-ONNX Other, 10 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.
- Qwen/Qwen3-0.6B752M15.7MReviewed
- PrimeIntellect/Qwen3-0.6B752M882kUnreviewed
- unsloth/Qwen3-0.6B-Base596M13kUnreviewed
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.