- Size
- 8.8B 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
- 11 Oct 2025the date the repo was created
- Context length
- 256k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)Qwen3VLForConditionalGeneration
- On Hugging Face
- Qwen/Qwen3-VL-8B-Instruct6.2M downloads in the last 30 days, 1.3k 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-VL-8B-Instruct), 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
Qwen/Qwen3-VL-8B-Instruct-GGUF (the maker's own conversion), 2.3M downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-Qwen3VL-8B-Instruct-F16.gguf (1.1 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q4_K_M | 4.7 GBfile size | 6.3 GB4.7 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen3-VL-8B-Instruct-GGUF:Q4_K_MOllama ollama run hf.co/Qwen/Qwen3-VL-8B-Instruct-GGUF:Q4_K_MDownload hf download Qwen/Qwen3-VL-8B-Instruct-GGUF --include "Qwen3VL-8B-Instruct-Q4_K_M.gguf" --local-dir Qwen3-VL-8B-Instruct-GGUF |
| Q8_0 | 8.1 GBfile size | 9.7 GB8.1 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen3-VL-8B-Instruct-GGUF:Q8_0Ollama ollama run hf.co/Qwen/Qwen3-VL-8B-Instruct-GGUF:Q8_0Download hf download Qwen/Qwen3-VL-8B-Instruct-GGUF --include "Qwen3VL-8B-Instruct-Q8_0.gguf" --local-dir Qwen3-VL-8B-Instruct-GGUF |
| F16 | 15.3 GBfile size | 16.9 GB15.3 + 1.1 + 0.50 | Commandsllama.cpp llama-server -hf Qwen/Qwen3-VL-8B-Instruct-GGUF:F16Ollama ollama run hf.co/Qwen/Qwen3-VL-8B-Instruct-GGUF:F16Download hf download Qwen/Qwen3-VL-8B-Instruct-GGUF --include "Qwen3VL-8B-Instruct-F16.gguf" --local-dir Qwen3-VL-8B-Instruct-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitlmstudio-community/Qwen3-VL-8B-Instruct-MLX-4bit | 5.4 GBfile size | 7.0 GB5.4 + 1.1 + 0.50 | Download page |
| MLX 8bitlmstudio-community/Qwen3-VL-8B-Instruct-MLX-8bit | 9.2 GBfile size | 10.8 GB9.2 + 1.1 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 16.3 GBfile size | 18.0 GB16.3 + 1.1 + 0.50 |
hf download Qwen/Qwen3-VL-8B-Instruct --local-dir Qwen3-VL-8B-InstructOther conversions (18; sizes not read)
- Qwen/Qwen3-VL-8B-Instruct-FP8 FP8, by the maker, 1.4M downloads
- cyankiwi/Qwen3-VL-8B-Instruct-AWQ-4bit AWQ, 4bit, 71k downloads
- unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit bitsandbytes, 4bit, 42k downloads
- SherlockID365/Qwen3-VL-8B-Instruct-quantized.w4a16 AWQ, w4a16, 5.8k downloads
- Vishva007/Qwen3-VL-8B-Instruct-W4A16-AutoRound Other, w4a16, 3.2k downloads
- unsloth/Qwen3-VL-8B-Instruct-bnb-4bit bitsandbytes, 4bit, 2.9k downloads
- mobilint/Qwen3-VL-8B-Instruct-Batch16 Other, 1.4k downloads
- lhoang8500/Qwen3-VL-8B-Instruct-NVFP4 NVFP4, 885 downloads
- OpenVINO/Qwen3-VL-8B-Instruct-int4-ov Other, int4, 789 downloads
- MLliu6/Qwen3-VL-8B-Instruct-AWQ-W4A16 AWQ, w4a16, 684 downloads
- JEILDLWLRMA/Qwen3-VL-8B-Instruct-NVFP4 NVFP4, 633 downloads
- mobilint/Qwen3-VL-8B-Instruct Other, 383 downloads
- Vishva007/Qwen3-VL-8B-Instruct-W4A16-AutoRound-AWQ AWQ, w4a16, 341 downloads
- Vishva007/Qwen3-VL-8B-Instruct-W4A16-AutoRound-GPTQ GPTQ, w4a16, 107 downloads
- simaai/Qwen3-VL-8B-Instruct-GPTQ-Safetensors GPTQ, 90 downloads
- mbehr90/Qwen3-VL-8B-Instruct-nvfp4 NVFP4, 80 downloads
- kaitchup/Qwen3-VL-8B-Instruct-NVFP4 NVFP4, 67 downloads
- turboderp/Qwen3-VL-8B-Instruct-exl3 EXL3, 42 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
2 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| Parasail | $0.25 | $0.75 | 256k | bf16 | 29 | 0.8 s | 100.0% | yes | yes |
| featherless-ai | ? | ? | ? | not given | ? | ? | ? | not given | not given |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "Qwen/Qwen3-VL-8B-Instruct:parasail", "messages": [{"role": "user", "content": "Hello"}]}'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.
- nvidia/Cosmos-Reason2-8B8.8B60kUnreviewed
- huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated8.8B27kUnreviewed
- RLWRLD/RLDX-1-VLM8.8B21kUnreviewed
- unsloth/Qwen3-VL-8B-Instruct8.8B6.6kUnreviewed
- monkeyslikebananas/Qwen3-VL-8B-NSFW-Caption-V4.58.8B2.9kUnreviewed
- microsoft/UniRG-CXR8.8B2.0kUnreviewed
- microsoft/AesCode-8B8.8B2.0kUnreviewed
- sensenova/SenseNova-MARS-8B8.8B580Unreviewed
- inclusionAI/ZwZ-8B8.8B520Unreviewed
- sensenova/SenseNova-SI-1.3-Qwen3-VL-8B8.8B257Unreviewed
- inclusionAI/ArmorOCR8.8B156Unreviewed
- sensenova/SenseNova-SI-1.1-Qwen3-VL-8B8.8B102Unreviewed
- sensenova/SenseNova-MARS-32B33.4B61Unreviewed
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.