Model reference · open weights

Qianfan-VL

LLMs baidu Vision + text 3 builds Its own licence terms 199 dl/mo

Qianfan-VL is an open-weight language model from Baidu. Qianfan-VL-70B (BF16) weighs 144 GB; the smallest configuration that runs it is 4× L40S 48 GB.

Qianfan-VL is a series of general-purpose multimodal large language models developed by Baidu for enterprise-level applications, with a focus on document understanding and OCR.
The Qianfan-VL-3B variant contains 3.7B parameters, supports a 32k context length, and is designed for edge deployment and real-time OCR tasks.
It supports English and Chinese languages and is released under an other license.

Summary of the baidu/Qianfan-VL-3B model card, 2026-10-01. The estimate below is for another build of the family.

Hugging Face ↗GitHub ↗Paper ↗

What it is

Released by	Baidu
Released	2025-09-16
Parameters	3.7B
VRAM	144 GB for the weights

What it runs on

Memory and cards for Qianfan-VL-70B (BF16)

144 GBweights, file size

328 MBcache per 1K tokens

2.3 GBruntime overhead, at least

32,768 tokenscontext max

Card	Requests at once		Context max	Memory
Card	8K each	32K each	Context max	Memory
RTX 3060 12 GB … H200 141 GB 11 smaller cards	—	—	—
B200 180 GB	8	2	all 32K	176 GB
4× L40S 48 GB tensor parallel	8	2	all 32K	44.0 GB a card
2× RTX PRO 6000 Blackwell 96 GB tensor parallel	10	2	all 32K	93.8 GB a card
2× H200 141 GB tensor parallel	43	10	all 32K	138 GB a card
4× H100 80 GB tensor parallel	51	12	all 32K	78.1 GB a card
4× A100 80 GB tensor parallel	59	14	all 32K	78.2 GB a card
2× B200 180 GB tensor parallel	71	17	all 32K	176 GB a card

Memory needed at each load

Requests at once	8K tokens each	32K tokens each
1	149 GB	157 GB
5	159 GB	200 GB
8	167 GB	232 GB
16	189 GB	318 GB
32	232 GB	490 GB
64	318 GB	833 GB

One card, with vLLM's small-card settings.

Builds

Sizes, precisions & builds

Build	Params	Precision	Weights	Smallest setup
Qianfan-VL-3B ↗	3.7B	BF16	7.4 GB	RTX 3060 12 GB
Qianfan-VL-8B ↗	8.8B	BF16	17.6 GB	2× RTX 3060 12 GB
Qianfan-VL-70B (above) ↗	71.8B	BF16	144 GB	4× L40S 48 GB

From the model card

What Baidu says about Qianfan-VL

Read the model card

Domain Capability Enhancement through Continuous Pre-training | 3B to 70B Parameter Scale | Document Understanding & OCR Enhancement | Chain-of-Thought Reasoning Support

🔗 Quick Links

Repository: 💻 GitHub
Models: 🤗 Hugging Face | 🤖 ModelScope
Documentation: 📚 Cookbook | 📝 Technical Report
Blogs: 🇨🇳 中文博客 | 🇬🇧 English Blog

Model Description

Qianfan-VL is a series of general-purpose multimodal large language models enhanced for enterprise-level multimodal applications. The models offer deep optimization for high-frequency scenarios in industrial deployment while maintaining strong general capabilities.

Model Variants

Model	Parameters	Context Length	CoT Support	Best For
Qianfan-VL-3B	3B	32k	❌	Edge deployment, real-time OCR
Qianfan-VL-8B	8B	32k	✅	Server-side general scenarios, fine-tuning
Qianfan-VL-70B	70B	32k	✅	Complex reasoning, data synthesis

Architecture

Language Model:
- Qianfan-VL-3B: Based on Qwen2.5-3B
- Qianfan-VL-8B/70B: Based on Llama 3.1 architecture
- Enhanced with 3T multilingual corpus
Vision Encoder: InternViT-based, supports dynamic patching up to 4K resolution
Cross-modal Fusion: MLP adapter for efficient vision-language bridging

Key Capabilities

🔍 OCR & Document Understanding

Full-Scenario OCR: Handwriting, formulas, natural scenes, cards/documents
Document Intelligence: Layout analysis, table parsing, chart understanding, document Q&A
High Precision: Industry-leading performance on OCR benchmarks

🧮 Chain-of-Thought Reasoning (8B & 70B)

Complex chart analysis and reasoning
Mathematical problem-solving with step-by-step derivation
Visual reasoning and logical inference
Statistical computation and trend prediction

📊 Benchmark Performance

General Vision-Language Benchmarks

Benchmark	Qianfan-VL-3B	Qianfan-VL-8B	Qianfan-VL-70B	InternVL-3-8B	InternVL-3-78B	Qwen2.5-VL-7B	Qwen2.5-VL-72B
A-Bench_VAL	75.65	75.72	78.1	75.86	75.86	76.49	79.22
CCBench	66.86	70.39	80.98	77.84	70.78	57.65	73.73
SEEDBench_IMG	76.55	78.02	79.13	77.0	77.52	76.98	78.34
SEEDBench2_Plus	67.59	70.97	73.17	69.52	68.47	70.93	73.25
MMVet	48.17	53.21	67.34	80.28	78.9	70.64	75.69
MMMU_VAL	46.44	47.11	58.33	56.11	60.78	51.0	65.78
ScienceQA_TEST	95.19	97.62	98.76	97.97	97.17	85.47	92.51
ScienceQA_VAL	93.85	97.62	98.81	97.81	95.14	83.59	91.32
MMT-Bench_VAL	62.23	63.22	71.06	65.17	63.67	61.4	69.49
MTVQA_TEST	26.5	30.14	32.18	30.3	27.62	29.08	31.48
BLINK	49.97	56.81	59.44	55.87	51.87	54.55	63.02
MMStar	57.93	64.07	69.47	68.4	66.07	61.53	66.0
RealWorldQA	65.75	70.59	71.63	71.11	74.25	69.28	73.86
Q-Bench1_VAL	73.51	75.25	77.46	75.99	77.99	78.1	79.93
POPE	85.08	86.06	88.97	90.59	88.87	85.97	83.35
RefCOCO (Avg)	85.94	89.37	91.01	89.65	91.40	86.56	90.25

OCR & Document Understanding

Benchmark	Qianfan-VL-3B	Qianfan-VL-8B	Qianfan-VL-70B	InternVL-3-8B	InternVL-3-78B	Qwen2.5-VL-3B	Qwen2.5-VL-7B	Qwen2.5-VL-72B
OCRBench	831	854	873	881	847	810	883	874
AI2D_TEST	81.38	85.07	87.23	85.07	83.55	77.07	80.472	83.84
OCRVQA_TEST	66.15	68.98	74.06	39.03	35.58	69.24	71.02	66.8
TextVQA_VAL	80.11	82.13	84.48	82.15	83.52	79.09	84.962	83.26
DocVQA_VAL	90.85	93.54	94.75	92.04	83.82	92.71	**9

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

Details

Type	Language models
Task	Vision + text
Runs with	transformers
Popularity	199 downloads / month
Weights	144 GB, Qianfan-VL-70B (BF16, file size)

Languages

enzh