granite-4.1-8b vs llava-onevision-qwen2-7b-ov

Specs, VRAM requirements and download trends — updated 6 August 2026.

ibm-granite · A
Params
8.8 B
Context
131,072
30d
4.2 M
apache-2.0 · commercial OK
lmms-lab · B
Params
8.0 B
Context
32,768
30d
194 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification granite-4.1-8b llava-onevision-qwen2-7b-ov
Parameters 8.8 B 8.0 B
Architecture GraniteForCausalLM LlavaQwenForCausalLM
Context length 131,072 32,768
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 2
Downloads 30d 4,208,265 194,138
Downloads all time 5.0 M 3.0 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-06 2024-06-29

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

4.2 M194 K
granite-4.1-8b llava-onevision-qwen2-7b-ov

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

llava-onevision-qwen2-7b-ov · fp16 19.4 GB / 24 GB
✅ Runs comfortably
granite-4.1-8b · fp16 @ 128K ctx 40.9 GB / 24 GB
❌ Won’t fit

Adjacent comparisons