granite-4.1-8b vs Apertus-70B-Instruct-2509-quantized.w4a16

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
RedHatAI · B
Params
11.3 B
Context
65,536
30d
338 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification granite-4.1-8b Apertus-70B-Instruct-2509-quantized.w4a16
Parameters 8.8 B 11.3 B
Architecture GraniteForCausalLM ApertusForCausalLM
Context length 131,072 65,536
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 4,208,265 337,908
Downloads all time 5.0 M 516 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-06 2025-09-21

Download trend

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

4.2 M226 K
granite-4.1-8b Apertus-70B-Instruct-2509-quantized.w4a16

VRAM side by side

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

granite-4.1-8b · fp16 @ 128K ctx 40.9 GB / 24 GB
❌ Won’t fit
Apertus-70B-Instruct-2509-quantized.w4a16 · fp16 46.0 GB / 24 GB
❌ Won’t fit

Adjacent comparisons