- 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
- Kind
- Base model (no base model declared on the Hub)Qwen3_5ForConditionalGeneration
- On Hugging Face
- Qwen/Qwen3.5-0.8B-Base872k downloads in the last 30 days, 141 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: 0.09 GB, worked out from the model's config (Qwen/Qwen3.5-0.8B-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/Qwen3.5-0.8B-Base-i1-GGUF (converted by mradermacher), 1.1k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 0.37 GBfile size | 0.96 GB0.37 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ3_XXSOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ3_XXSDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-IQ3_XXS.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q3_K_S | 0.41 GBfile size | 1.00 GB0.41 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q3_K_SOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q3_K_SDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q3_K_S.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| IQ3_XS | 0.41 GBfile size | 1.0 GB0.41 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ3_XSOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ3_XSDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-IQ3_XS.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| IQ3_S | 0.42 GBfile size | 1.0 GB0.42 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ3_SOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ3_SDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-IQ3_S.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| IQ3_M | 0.42 GBfile size | 1.0 GB0.42 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ3_MOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ3_MDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-IQ3_M.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q3_K_M | 0.43 GBfile size | 1.0 GB0.43 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q3_K_MOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q3_K_MDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q3_K_M.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q3_K_L | 0.46 GBfile size | 1.1 GB0.46 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q3_K_LOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q3_K_LDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q3_K_L.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q4_0 | 0.47 GBfile size | 1.1 GB0.47 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q4_0Ollama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q4_0Download hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q4_0.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| IQ4_XS | 0.47 GBfile size | 1.1 GB0.47 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ4_XSOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ4_XSDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-IQ4_XS.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q4_K_S | 0.47 GBfile size | 1.1 GB0.47 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q4_K_SOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q4_K_SDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q4_K_S.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| IQ4_NL | 0.48 GBfile size | 1.1 GB0.48 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ4_NLOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:IQ4_NLDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-IQ4_NL.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q4_K_M | 0.49 GBfile size | 1.1 GB0.49 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q4_K_MOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q4_K_MDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q4_K_M.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q4_1 | 0.50 GBfile size | 1.1 GB0.50 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q4_1Ollama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q4_1Download hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q4_1.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q5_K_S | 0.52 GBfile size | 1.1 GB0.52 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q5_K_SOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q5_K_SDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q5_K_S.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q5_K_M | 0.54 GBfile size | 1.1 GB0.54 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q5_K_MOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q5_K_MDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q5_K_M.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
| Q6_K | 0.59 GBfile size | 1.2 GB0.59 + 0.09 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q6_KOllama ollama run hf.co/mradermacher/Qwen3.5-0.8B-Base-i1-GGUF:Q6_KDownload hf download mradermacher/Qwen3.5-0.8B-Base-i1-GGUF --include "Qwen3.5-0.8B-Base.i1-Q6_K.gguf" --local-dir Qwen3.5-0.8B-Base-i1-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitMuesli-HQ/qwen35-0.8b-base-cotypist-mlx-4bit | 0.39 GBfile size | 0.99 GB0.39 + 0.09 + 0.50 | Download page |
| MLX 4bitbluevisor/Qwen3.5-0.8B-Base-4bit-mlx | 0.39 GBfile size | 0.99 GB0.39 + 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-Base --local-dir Qwen3.5-0.8B-BaseOther conversions (6; sizes not read)
- AxionML/Qwen3.5-0.8B-Base-NVFP4 NVFP4, 53 downloads
- taobao-mnn/Qwen3.5-0.8B-Base-MNN Other, 40 downloads
- LeaderboardModel1/Qwen3.5-0.8B-Base-autoround-NVFP4 NVFP4, 38 downloads
- labeebaryan/Qwen3.5-0.8B-Base-CliffQuant-W4A16-G128 GPTQ, w4a16, 18 downloads
- LeaderboardModel1/Qwen3.5-0.8B-Base-autoround-MXFP4 Other, mxfp4, 16 downloads
- mistralrs-community/Qwen3.5-0.8B-Base-UQFF Other, 12 downloads
The Hub tags 60 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/Qwen3.5-0.8B873M2.7MReviewed
- xiaomi-research/Xiaomi-OCR-0873M38kUnreviewed
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.