Qianfan VL 70B
Sep 2025
Qianfan VL 70BCompare inonMMMU validation
—per task?
self-host onlyprice
—output speed?
33Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.1unstated+46%—$1.25 / $10
OpenSkywork R1V3 38B+30%——Bettero3unstated+42%—$2 / $8
BetterClaude Opus 4.5unstated+38%—$5 / $25dBetterDots.vlm1.instOpen+37%——Memory (4-bit): not verifiedModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5.1unstated+46%—$1.25 / $10o3unstated+42%—$2 / $8Claude Opus 4.5unstated+38%—$5 / $25dDots.vlm1.instOpen+37%——Memory (4-bit): not verified
Gemini 2.5 Pro Preview (May' 25)unstated+37%——No image input
Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✓ 48 GB GPU · compressed✓ 80 GB GPU · 8-bit
LicenceMITfree for commercial use
Benchmarks
in Vision & DocumentsMMMU · validation58.3#26
FAQ
How much does Qianfan VL 70B cost?›
There is no per-unit API price: self-host only.
Is Qianfan VL 70B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Qianfan VL 70B, and what is it best at?›
#26 of 41 in Vision & Documents.
Is Qianfan VL 70B better than GPT-4o Mini?›
On MMMU · validation, Qianfan VL 70B scores 58.3 vs 59.4 — lower.
What is the context window of Qianfan VL 70B?›
33K tokens.
When was Qianfan VL 70B released? Is there a newer version?›
Released 2025-09-23. It is the current version in its line.
Is Qianfan VL 70B open source?›
Yes, the weights are open (MIT licence).
Can I run Qianfan VL 70B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qianfan VL 70B read images?›
It accepts text and images as input.
What is Qianfan VL 70B?›
Qianfan VL 70B is an open-weights language model from Baidu, released Sep 2025.
What are the best alternatives to Qianfan VL 70B?›
GPT-5.1 (better), Skywork R1V3 38B (open weights).