Qwen · fine-tune of Qwen/Qwen2-VL-72B
QVQ-72B-Preview
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: 2.5 GB, worked out from the model's config (Qwen/QVQ-72B-Preview), 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
bartowski/QVQ-72B-Preview-GGUF (converted by bartowski), 2.5k downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-QVQ-72B-Preview-f16.gguf (1.3 GB), not counted below. Showing the common levels.
| Format | Size | Memory needed | Memory | Get it |
|---|---|---|---|---|
| Q4_K_M | 44.2 GBfile size | 47.2 GB44.2 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/QVQ-72B-Preview-GGUF:Q4_K_MOllama ollama run hf.co/bartowski/QVQ-72B-Preview-GGUF:Q4_K_MDownload hf download bartowski/QVQ-72B-Preview-GGUF --include "QVQ-72B-Preview-Q4_K_M.gguf" --local-dir QVQ-72B-Preview-GGUF | |
| Q5_K_M | 50.7 GBfile size, 2 parts | 53.7 GB50.7 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/QVQ-72B-Preview-GGUF:Q5_K_MDownload hf download bartowski/QVQ-72B-Preview-GGUF --include "QVQ-72B-Preview-Q5_K_M/QVQ-72B-Preview-Q5_K_M-*-of-00002.gguf" --local-dir QVQ-72B-Preview-GGUF | |
| Q6_K | 59.9 GBfile size, 2 parts | 62.9 GB59.9 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/QVQ-72B-Preview-GGUF:Q6_KDownload hf download bartowski/QVQ-72B-Preview-GGUF --include "QVQ-72B-Preview-Q6_K/QVQ-72B-Preview-Q6_K-*-of-00002.gguf" --local-dir QVQ-72B-Preview-GGUF | |
| Q8_0 | 72.0 GBfile size, 2 parts | 75.0 GB72.0 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/QVQ-72B-Preview-GGUF:Q8_0Download hf download bartowski/QVQ-72B-Preview-GGUF --include "QVQ-72B-Preview-Q8_0/QVQ-72B-Preview-Q8_0-*-of-00002.gguf" --local-dir QVQ-72B-Preview-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Memory | Repo |
|---|---|---|---|---|
| BF16original weights | 136.7 GBfile size | 139.7 GB136.7 + 2.5 + 0.50 |
hf download Qwen/QVQ-72B-Preview --local-dir QVQ-72B-PreviewOther conversions (6; sizes not read)
- unsloth/QVQ-72B-Preview-bnb-4bit bitsandbytes, 4bit, 135 downloads
- kosbu/QVQ-72B-Preview-AWQ AWQ, 29 downloads
- bullerwins/QVQ-72B-Preview-exl2_5.0bpw EXL2, 25 downloads
- Dracones/QVQ-72B-Preview_exl2_8.0bpw EXL2, 24 downloads
- Dracones/QVQ-72B-Preview_exl2_4.5bpw EXL2, 24 downloads
- Dracones/QVQ-72B-Preview_exl2_4.0bpw EXL2, 24 downloads
The Hub tags 24 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.
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, 15:15 UTC. The repo. Found a mistake on this page? Tell us.