Llama-3.1-8B-Instruct vs gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2
Specs, VRAM requirements and download trends — updated 6 August 2026.
yuxinlu1 · B
Params
12.0 B
Context
—
30d
266 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.1-8B-Instruct | gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2 |
|---|---|---|
| Parameters | 8.0 B | 12.0 B |
| Architecture | LlamaForCausalLM | Gemma4UnifiedForConditionalGeneration |
| Context length | — | — |
| Licence | llama3.1 | apache-2.0 |
| Commercial use | Conditional | Allowed |
| Languages | 8 | — |
| Downloads 30d | 8,014,793 | 266,452 |
| Downloads all time | 175.3 M | 275 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-18 | 2026-06-28 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
8.0 M206 K
Llama-3.1-8B-Instruct
gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.1-8B-Instruct · fp16
19.4 GB / 24 GB
gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2 · fp16
28.6 GB / 24 GB