Llama-3.1-8B-Instruct vs gemma-2-9b-it-AWQ-INT4
Specs, VRAM requirements and download trends — updated 6 August 2026.
hugging-quants · B
Params
9.2 B
Context
8,192
30d
504 K
gemma licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.1-8B-Instruct | gemma-2-9b-it-AWQ-INT4 |
|---|---|---|
| Parameters | 8.0 B | 9.2 B |
| Architecture | LlamaForCausalLM | Gemma2ForCausalLM |
| Context length | — | 8,192 |
| Licence | llama3.1 | gemma |
| Commercial use | Conditional | Conditional |
| Languages | 8 | 1 |
| Downloads 30d | 8,014,793 | 504,472 |
| Downloads all time | 175.3 M | 605 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-18 | 2024-10-15 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
8.0 M311 K
Llama-3.1-8B-Instruct
gemma-2-9b-it-AWQ-INT4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gemma-2-9b-it-AWQ-INT4 · fp16
8.7 GB / 24 GB
Llama-3.1-8B-Instruct · fp16
19.4 GB / 24 GB