- Size
- 752M 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
- 23 Sep 2025the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Fine-tune
- of Qwen/Qwen3-0.6BQwen3ForCausalLM
- On Hugging Face
- Qwen/Qwen3Guard-Gen-0.6B144k downloads in the last 30 days, 102 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/Qwen3Guard-Gen-0.6B), 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/Qwen3Guard-Gen-0.6B-GGUF (converted by mradermacher), 3.1k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 0.32 GBfile size | 1.7 GB0.32 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q2_KOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q2_KDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q2_K.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q3_K_S | 0.36 GBfile size | 1.7 GB0.36 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q3_K_SOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q3_K_SDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q3_K_S.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q3_K_M | 0.39 GBfile size | 1.8 GB0.39 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q3_K_MOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q3_K_MDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q3_K_M.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q3_K_L | 0.41 GBfile size | 1.8 GB0.41 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q3_K_LOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q3_K_LDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q3_K_L.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| IQ4_XS | 0.42 GBfile size | 1.8 GB0.42 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:IQ4_XSOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:IQ4_XSDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.IQ4_XS.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q4_K_S | 0.44 GBfile size | 1.8 GB0.44 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q4_K_SOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q4_K_SDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q4_K_S.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q4_K_M | 0.45 GBfile size | 1.8 GB0.45 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q4_K_MOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q4_K_MDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q4_K_M.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q5_K_S | 0.51 GBfile size | 1.9 GB0.51 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q5_K_SOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q5_K_SDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q5_K_S.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q5_K_M | 0.51 GBfile size | 1.9 GB0.51 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q5_K_MOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q5_K_MDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q5_K_M.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q6_K | 0.58 GBfile size | 2.0 GB0.58 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q6_KOllama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q6_KDownload hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q6_K.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| Q8_0 | 0.75 GBfile size | 2.1 GB0.75 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q8_0Ollama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:Q8_0Download hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.Q8_0.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
| F16 | 1.4 GBfile size | 2.8 GB1.4 + 0.88 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3Guard-Gen-0.6B-GGUF:F16Ollama ollama run hf.co/mradermacher/Qwen3Guard-Gen-0.6B-GGUF:F16Download hf download mradermacher/Qwen3Guard-Gen-0.6B-GGUF --include "Qwen3Guard-Gen-0.6B.f16.gguf" --local-dir Qwen3Guard-Gen-0.6B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX mxfp4abnormalmapstudio/Qwen3Guard-Gen-0.6B-mxfp4-mlx | 0.30 GBfile size | 1.7 GB0.30 + 0.88 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 1.4 GBfile size | 2.8 GB1.4 + 0.88 + 0.50 |
hf download Qwen/Qwen3Guard-Gen-0.6B --local-dir Qwen3Guard-Gen-0.6BOther conversions (5; sizes not read)
- geoffmunn/Qwen3Guard-Gen-0.6B GGUF, 70 downloads
- nxp/Qwen3Guard-Gen-0.6B-ONNX Other, 20 downloads
- Cwkisgo/Qwen3Guard-Gen-0.6B-q4f16_1-MLC Other, 18 downloads
- mistralrs-community/Qwen3Guard-Gen-0.6B-UQFF Other, 4 downloads
- peonist-ai/halogen-npu-qwen3guard-gen-0.6b Other, 0 downloads
The Hub tags 17 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.
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.