Qianfan VL 8B
Sep 2025
Qianfan VL 8BCompare inonMMMU validation
—per task?
self-host onlyprice
—output speed?
33Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.1unstated+81%—$1.25 / $10
OpenMiMo VL 7B RL+42%——Bettero3unstated+76%—$2 / $8
BetterClaude Opus 4.5unstated+71%—$5 / $25dBetterDots.vlm1.instOpen+70%——Memory (4-bit): not verifiedModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5.1unstated+81%—$1.25 / $10o3unstated+76%—$2 / $8Claude Opus 4.5unstated+71%—$5 / $25dDots.vlm1.instOpen+70%——Memory (4-bit): not verified
Gemini 2.5 Pro Preview (May' 25)unstated+69%——No image input
Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
Licencecustom licencecommercial use with conditions
Benchmarks
in Vision & DocumentsMMMU · validation47.1#34
FAQ
How much does Qianfan VL 8B cost?›
There is no per-unit API price: self-host only.
Is Qianfan VL 8B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Qianfan VL 8B, and what is it best at?›
#34 of 41 in Vision & Documents.
Is Qianfan VL 8B better than Gemini 1.0 Pro?›
On MMMU · validation, Qianfan VL 8B scores 47.1 vs 47.9 — about the same.
What is the context window of Qianfan VL 8B?›
33K tokens.
When was Qianfan VL 8B released? Is there a newer version?›
Released 2025-09-23. It is the current version in its line.
Is Qianfan VL 8B open source?›
Yes, the weights are open.
Can I run Qianfan VL 8B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qianfan VL 8B read images?›
It accepts text and images as input.
What is Qianfan VL 8B?›
Qianfan VL 8B is an open-weights language model from Baidu, released Sep 2025.
What are the best alternatives to Qianfan VL 8B?›
GPT-5.1 (better), MiMo VL 7B RL (open weights).