lmms-lab / text-generation updated 1 year ago

llava-onevision-qwen2-7b-ov

Name: llava-onevision-qwen2-7b-ov
Author: lmms-lab

The LLaVA-OneVision models are 0.5/7/72B parameter models trained on LLaVA-OneVision, based on Qwen2 language model with a context window of 32K tokens.

Params

8.0 B

Context

32,768

Downloads 30d

194 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

214 K194 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	16.1 GB	19.4 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 32K ctx	16.1 GB	23.0 GB	⚠️ Tight — reduce context

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/llava-onevision-qwen2-7b-ov
{
  "hf_id": "lmms-lab/llava-onevision-qwen2-7b-ov",
  "params_b": 8.03,
  "context_length": 32768,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 194138,
  "vram_estimates": [
    { "quant": "bf16", "gb": 19.4 }
  ],
  "updated_at": "2026-07-28T18:07:52Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: LlavaQwenForCausalLM
Parameters: 8.0 B
Tensor type: BF16
Context length: 32,768
Vocabulary: 152,064
Layers / heads: 28 / 28
Licence: apache-2.0
First seen on the Hub: 2024-06-29
Training datasets: lmms-lab/LLaVA-OneVision-Data
AI2D (reported): 81.4
MMMU (reported): 48.8
MMVet (reported): 57.5
DocVQA (reported): 90.2
MMStar (reported): 61.7
ChartQA (reported): 80
InfoVQA (reported): 70.7
MMBench (reported): 80.8
MathVerse (reported): 26.2
MathVista (reported): 63.2
MME-Cognition (reported): 418
MME-Perception (reported): 1580
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB