AL
Alibaba
Language model · China ·Dec 2024

QVQ

Language Open (Restricted)
72B
Parameters
2
Benchmarks

About QVQ

QVQ is an AI model developed by Alibaba, in the language category, released in 2024, made available as an open-weights model with 72B params.

On this page you'll find QVQ's full specifications, including 2 benchmark results. Review provider pricing and benchmark scores below, or compare QVQ head-to-head with other language models.

→ More models by Alibaba → All language models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run QVQ locally — what to buy

Share this build ↗

Sized to what QVQ actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Best
Apple M1 Ultra 64GB
Apple · ~$3,700
~16.3 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
4.9–5.9 tok/s
2 options →
Apple
8.1–16.3 tok/s
13 options →
Datacenter GPU
16.5–120+ tok/s
13 options →

Community

Would you run QVQ again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

QVQ benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
MMMU multimodal 70.3% val-from-hf-readme
MathVista multimodal 71.4% mini-from-hf-readme

More models like QVQ

AI
DMind-1
 AI
COLLECTIVE-1
 AI
Cogito 1 series
 AI
Euler (Euler大模型)
· 2.5B
 AI
SmolLM-1.7B
· 1.7B
 AI
Llama-3-70B-Synthia-v3.5
· 70B

Frequently asked questions

What is QVQ? ▶

QVQ is an AI model developed by Alibaba, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created QVQ? ▶

QVQ was developed by Alibaba and released in 2024.

Is QVQ open source or proprietary? ▶

QVQ ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does QVQ cost? ▶

Pricing for QVQ depends on the provider. See the providers table on this page for the latest API rates.

How does QVQ perform on benchmarks? ▶

QVQ is benchmarked across 2 evaluations on GenAIList, including MMMU (70.3%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about QVQ?