- Size
- 873M 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
- 28 Feb 2026the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Fine-tune
- of Qwen/Qwen3.5-0.8B-BaseQwen3_5ForConditionalGeneration
- On Hugging Face
- Qwen/Qwen3.5-0.8B2.7M downloads in the last 30 days, 852 likes
Scores
- default setting0.0%via Epoch AI
- effort none0.0%via Epoch AI
Epoch's name: qwen3.5-0.8b. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 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: 0.09 GB, worked out from the model's config (Qwen/Qwen3.5-0.8B), 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
turintech/Qwen3.5-0.8B-Artemis-GGUF (converted by turintech), 696k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-F16.gguf (0.19 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q4_K_M | 0.50 GBfile size | 1.1 GB0.50 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf turintech/Qwen3.5-0.8B-Artemis-GGUF:Q4_K_MOllama ollama run hf.co/turintech/Qwen3.5-0.8B-Artemis-GGUF:Q4_K_MDownload hf download turintech/Qwen3.5-0.8B-Artemis-GGUF --include "Qwen3.5-0.8B-Artemis-Q4_K_M.gguf" --local-dir Qwen3.5-0.8B-Artemis-GGUF |
| Q5_K_M | 0.53 GBfile size | 1.1 GB0.53 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf turintech/Qwen3.5-0.8B-Artemis-GGUF:Q5_K_MOllama ollama run hf.co/turintech/Qwen3.5-0.8B-Artemis-GGUF:Q5_K_MDownload hf download turintech/Qwen3.5-0.8B-Artemis-GGUF --include "Qwen3.5-0.8B-Artemis-Q5_K_M.gguf" --local-dir Qwen3.5-0.8B-Artemis-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitmlx-community/Qwen3.5-0.8B-MLX-4bit | 0.58 GBfile size | 1.2 GB0.58 + 0.09 + 0.50 | Download page |
| MLX 4bitlmstudio-community/Qwen3.5-0.8B-MLX-4bit | 0.58 GBfile size | 1.2 GB0.58 + 0.09 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 1.6 GBfile size | 2.2 GB1.6 + 0.09 + 0.50 |
hf download Qwen/Qwen3.5-0.8B --local-dir Qwen3.5-0.8BOther conversions (5; sizes not read)
- onnx-community/Qwen3.5-0.8B-ONNX Other, 55k downloads
- Zerul/Qwen3.5-0.8B-W4A16-AutoRound-AWQ AWQ, w4a16, 37k downloads
- litert-community/Qwen3.5-0.8B Other, 6.9k downloads
- onnx-community/Qwen3.5-0.8B-ONNX-OPT Other, 3.3k downloads
- onnx-community/Qwen3.5-0.8B-Text-ONNX Other, 1.9k 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.
- ATH-MaaS/OvisOCR3853M376kUnreviewed
- unsloth/Qwen3.5-0.8B873M64kUnreviewed
- ATH-MaaS/OvisOCR2853M25kUnreviewed
- Hcompany/Holo-3.1-0.8B1.1B11kUnreviewed
- RikiyaT/Qwen3.5-0.8B-weight-space-programming873M5.8kUnreviewed
- JonathanColetti/Qwen3.5-0.8B-Astra-WeightEdit873M4.8kUnreviewed
- internlm/Intern-Decision-0.8B853M4.2kUnreviewed
- OmniJev/OneJev1.6-0.8B853M3.1kUnreviewed
- qvac/BotPsy-0.8B853M1.3kUnreviewed
- THUSI-Lab/GameScaling892Unreviewed
- THUSI-Lab/GameScaling-0.8B-S11.1B573Unreviewed
- nvidia/Qwen3.5-0.8B-Qwen3.8-27B-Draft752M261Unreviewed
- rilixai/Qwen3.5-0.8B-Beaker-math-all-fixes873M185Unreviewed
- Cactus-Compute/Qwen3.5-0.8B16Unreviewed
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.