Qwen3-8B vs granite-4.1-3b

Specs, VRAM requirements and download trends — updated 20 September 2026.

Qwen · A
Params
8.2 B
Context
40,960
30d
12.9 M
apache-2.0 · commercial OK
ibm-granite · B
Params
3.4 B
Context
131,072
30d
380 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-8B granite-4.1-3b
Parameters 8.2 B 3.4 B
Architecture Qwen3ForCausalLM GraniteForCausalLM
Context length 40,960 131,072
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 12,931,851 380,081
Downloads all time 123.7 M 1.3 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2026-04-06

Download trend

Daily snapshots, last 55 days (28 Jul – 20 Sep)

16.6 M185 K
Qwen3-8B granite-4.1-3b

VRAM side by side

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

granite-4.1-3b · fp16 @ 128K ctx 16.1 GB / 24 GB
✅ Runs comfortably
Qwen3-8B · fp16 19.7 GB / 24 GB
⚠️ Tight — reduce context

Adjacent comparisons