Qwen · fine-tune of Qwen/Qwen2-VL-2B
Qwen2-VL-2B-Instruct
Runs on your machine
Choose a machine
We then show the largest format that fits, from real file sizes where we have them.
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: 0.22 GB, worked out from the model's config (Qwen/Qwen2-VL-2B-Instruct), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
weights context cache runtime
GGUF for llama.cpp, Ollama, LM Studio and others
ggml-org/Qwen2-VL-2B-Instruct-GGUF (converted by ggml-org), 23k 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-2B-Instruct-f16.gguf (1.2 GB), not counted below.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| Q4_K_M | 0.92 GBfile size | 1.6 GB0.92 + 0.22 + 0.50 | Commandsllama.cpp llama-server -hf ggml-org/Qwen2-VL-2B-Instruct-GGUF:Q4_K_MOllama ollama run hf.co/ggml-org/Qwen2-VL-2B-Instruct-GGUF:Q4_K_MDownload hf download ggml-org/Qwen2-VL-2B-Instruct-GGUF --include "Qwen2-VL-2B-Instruct-Q4_K_M.gguf" --local-dir Qwen2-VL-2B-Instruct-GGUF | |
| Q8_0 | 1.5 GBfile size | 2.3 GB1.5 + 0.22 + 0.50 | Commandsllama.cpp llama-server -hf ggml-org/Qwen2-VL-2B-Instruct-GGUF:Q8_0Ollama ollama run hf.co/ggml-org/Qwen2-VL-2B-Instruct-GGUF:Q8_0Download hf download ggml-org/Qwen2-VL-2B-Instruct-GGUF --include "Qwen2-VL-2B-Instruct-Q8_0.gguf" --local-dir Qwen2-VL-2B-Instruct-GGUF | |
| F16 | 2.9 GBfile size | 3.6 GB2.9 + 0.22 + 0.50 | Commandsllama.cpp llama-server -hf ggml-org/Qwen2-VL-2B-Instruct-GGUF:F16Ollama ollama run hf.co/ggml-org/Qwen2-VL-2B-Instruct-GGUF:F16Download hf download ggml-org/Qwen2-VL-2B-Instruct-GGUF --include "Qwen2-VL-2B-Instruct-f16.gguf" --local-dir Qwen2-VL-2B-Instruct-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 4.1 GBfile size | 4.8 GB4.1 + 0.22 + 0.50 |
hf download Qwen/Qwen2-VL-2B-Instruct --local-dir Qwen2-VL-2B-InstructOther conversions (11; sizes not read)
- Qwen/Qwen2-VL-2B-Instruct-AWQ AWQ, by the maker, 119k downloads
- Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4 GPTQ, int4, by the maker, 893 downloads
- Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8 GPTQ, int8, by the maker, 814 downloads
- unsloth/Qwen2-VL-2B-Instruct-unsloth-bnb-4bit bitsandbytes, 4bit, 7.4k downloads
- onnx-community/Qwen2-VL-2B-Instruct Other, 1.4k downloads
- unsloth/Qwen2-VL-2B-Instruct-bnb-4bit bitsandbytes, 4bit, 1.4k downloads
- mobilint/Qwen2-VL-2B-Instruct Other, 907 downloads
- cydxg/Qwen2-VL-2B-Instruct-OpenVINO-INT4 Other, int4, 75 downloads
- pdufour/Qwen2-VL-2B-Instruct-ONNX-Q4-F16 Other, 35 downloads
- h2oai/Qwen2-VL-2B-Instruct-GPTQ-Int4 GPTQ, int4, 16 downloads
- Zenabius/Qwen2-VL-2B-Instruct-exl2 EXL2, 11 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
- numind/NuExtract-2.0-2B2.2B7.4kUnreviewed
- microsoft/GUI-Actor-2B-Qwen2-VL2.2B567Unreviewed
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.