- Size
- 8.3B 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 Aug 2024the date the repo was created
- Context length
- 32k tokensfrom the model's config
- Fine-tune
- of Qwen/Qwen2-VL-7BQwen2VLForConditionalGeneration
- On Hugging Face
- Qwen/Qwen2-VL-7B-Instruct550k downloads in the last 30 days, 1.3k likes
Scores
- default setting3.7%±0.825 Nov 2024, balrogai.com
Epoch's name: Qwen2-VL-7B-Instruct. Best closed model on this set: gpt-6-astra_max, 68.3% (OpenAI). All 41 results
- default setting63.9%Video-MME Leaderboard
Epoch's name: Qwen2-VL-7B-Instruct. Best closed model on this set: gemini-1.5-pro-001, 75.0% (Google DeepMind). All 50 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: 0.44 GB, worked out from the model's config (Qwen/Qwen2-VL-7B-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
bartowski/Qwen2-VL-7B-Instruct-GGUF (converted by bartowski), 20k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-Qwen2-VL-7B-Instruct-f16.gguf (1.3 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XS | 3.1 GBfile size | 4.1 GB3.1 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:IQ3_XSOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:IQ3_XSDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-IQ3_XS.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q3_K_S | 3.3 GBfile size | 4.2 GB3.3 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q3_K_SOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q3_K_SDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q3_K_S.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| IQ3_M | 3.3 GBfile size | 4.3 GB3.3 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:IQ3_MOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:IQ3_MDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-IQ3_M.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q3_K_M | 3.5 GBfile size | 4.5 GB3.5 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q3_K_MOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q3_K_MDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q3_K_M.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q3_K_L | 3.8 GBfile size | 4.7 GB3.8 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q3_K_LOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q3_K_LDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q3_K_L.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| IQ4_XS | 3.9 GBfile size | 4.9 GB3.9 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:IQ4_XSOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:IQ4_XSDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-IQ4_XS.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| IQ4_NL | 4.1 GBfile size | 5.1 GB4.1 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:IQ4_NLOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:IQ4_NLDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-IQ4_NL.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q4_0 | 4.1 GBfile size | 5.1 GB4.1 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q4_0Ollama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q4_0Download hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q4_0.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q4_K_S | 4.2 GBfile size | 5.1 GB4.2 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q4_K_SOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q4_K_SDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q4_K_S.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q3_K_XL | 4.3 GBfile size | 5.2 GB4.3 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q3_K_XLOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q3_K_XLDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q3_K_XL.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q4_K_M | 4.4 GBfile size | 5.3 GB4.4 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q4_K_MOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q4_K_MDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q4_K_M.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q4_K_L | 4.7 GBfile size | 5.7 GB4.7 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q4_K_LOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q4_K_LDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q4_K_L.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q5_K_S | 5.0 GBfile size | 5.9 GB5.0 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q5_K_SOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q5_K_SDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q5_K_S.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q5_K_M | 5.1 GBfile size | 6.0 GB5.1 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q5_K_MOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q5_K_MDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q5_K_M.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q5_K_L | 5.4 GBfile size | 6.3 GB5.4 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q5_K_LOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q5_K_LDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q5_K_L.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q6_K | 5.8 GBfile size | 6.8 GB5.8 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q6_KOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q6_KDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q6_K.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q6_K_L | 6.1 GBfile size | 7.0 GB6.1 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q6_K_LOllama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q6_K_LDownload hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q6_K_L.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| Q8_0 | 7.5 GBfile size | 8.5 GB7.5 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:Q8_0Ollama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:Q8_0Download hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-Q8_0.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
| F16 | 14.2 GBfile size | 15.1 GB14.2 + 0.44 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Qwen2-VL-7B-Instruct-GGUF:F16Ollama ollama run hf.co/bartowski/Qwen2-VL-7B-Instruct-GGUF:F16Download hf download bartowski/Qwen2-VL-7B-Instruct-GGUF --include "Qwen2-VL-7B-Instruct-f16.gguf" --local-dir Qwen2-VL-7B-Instruct-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 15.4 GBfile size | 16.4 GB15.4 + 0.44 + 0.50 |
hf download Qwen/Qwen2-VL-7B-Instruct --local-dir Qwen2-VL-7B-InstructOther conversions (15; sizes not read)
- Qwen/Qwen2-VL-7B-Instruct-AWQ AWQ, by the maker, 77k downloads
- Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4 GPTQ, int4, by the maker, 965 downloads
- Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8 GPTQ, int8, by the maker, 788 downloads
- unsloth/Qwen2-VL-7B-Instruct-unsloth-bnb-4bit bitsandbytes, 4bit, 4.2k downloads
- unsloth/Qwen2-VL-7B-Instruct-bnb-4bit bitsandbytes, 4bit, 982 downloads
- nm-testing/Qwen2-VL-7B-Instruct-FP8-dynamic FP8, 321 downloads
- OpenVINO/Qwen2-VL-7B-Instruct-int4-ov Other, int4, 265 downloads
- Gabriel/Qwen2-VL-7B-Instruct-AWQ AWQ, 27 downloads
- OPEA/Qwen2-VL-7B-Instruct-int4-sym-inc Other, int4, 26 downloads
- p-christ/Qwen2-VL-7B-Instruct-AWQ AWQ, 22 downloads
- pdufour/Qwen2-VL-7B-Instruct-onnx Other, 21 downloads
- ruben3010/Qwen2-VL-7B-Instruct-AWQ-IE AWQ, 18 downloads
- OpenVINO/Qwen2-VL-7B-Instruct-fp16-ov Other, fp16, 17 downloads
- billatsectorflow/Qwen2-VL-7B-Instruct-GPTQ-Int4 GPTQ, int4, 8 downloads
- Zenabius/Qwen2-VL-7B-Instruct-exl2 EXL2, 6 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.
- allenai/olmOCR-7B-0225-preview8.3B35kReviewed
- microsoft/GUI-Actor-7B-Qwen2-VL8.4B445Unreviewed
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.