granite-4.1-8b vs deepseek-coder-7b-instruct-v1.5

Specs, VRAM requirements and download trends — updated 30 August 2026.

ibm-granite · A · Open weights
Params
8.8 B
Context
131,072
30d
192 K
apache-2.0 · commercial OK
deepseek-ai · B · Open weights
Params
6.9 B
Context
4,096
30d
172 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification granite-4.1-8b deepseek-coder-7b-instruct-v1.5
Parameters 8.8 B 6.9 B
Architecture GraniteForCausalLM LlamaForCausalLM
Context length 131,072 4,096
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages — —
Downloads 30d 192,200 172,053
Downloads all time 6.1 M 4.1 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-06 2024-01-25

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

4.2 M172 K
granite-4.1-8b deepseek-coder-7b-instruct-v1.5 A overtook B on 9 Nov

VRAM side by side

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

deepseek-coder-7b-instruct-v1.5 · fp16 16.7 GB / 24 GB
✅ Runs comfortably
granite-4.1-8b · fp16 @ 128K ctx 40.9 GB / 24 GB
❌ Won’t fit

Adjacent comparisons