Llama-3.1-8B-Instruct vs Apertus-70B-Instruct-2509-quantized.w4a16
Specs, VRAM requirements and download trends — updated 6 August 2026.
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 | Llama-3.1-8B-Instruct | Apertus-70B-Instruct-2509-quantized.w4a16 |
|---|---|---|
| Parameters | 8.0 B | 11.3 B |
| Architecture | LlamaForCausalLM | ApertusForCausalLM |
| Context length | — | 65,536 |
| Licence | llama3.1 | apache-2.0 |
| Commercial use | Conditional | Allowed |
| Languages | 8 | — |
| Downloads 30d | 8,014,793 | 337,908 |
| Downloads all time | 175.3 M | 516 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-18 | 2025-09-21 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
8.0 M226 K
Llama-3.1-8B-Instruct
Apertus-70B-Instruct-2509-quantized.w4a16
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.1-8B-Instruct · fp16
19.4 GB / 24 GB
Apertus-70B-Instruct-2509-quantized.w4a16 · fp16
46.0 GB / 24 GB