Llama-3.1-405B-FP8 vs Qwen3-Coder-480B-A35B-Instruct-FP8
Specs, VRAM requirements and download trends — updated 21 September 2026.
Qwen · B
Params
480.2 B
Context
262,144
30d
804 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Llama-3.1-405B-FP8 | Qwen3-Coder-480B-A35B-Instruct-FP8 |
|---|---|---|
| Parameters | 405.9 B | 480.2 B |
| Architecture | LlamaForCausalLM | Qwen3MoeForCausalLM |
| Context length | — | 262,144 |
| Licence | llama3.1 | apache-2.0 |
| Commercial use | Conditional | Allowed |
| Languages | 8 | — |
| Downloads 30d | 465,220 | 803,619 |
| Downloads all time | 1.9 M | 3.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | Yes — accept licence | No |
| First seen on the Hub | 2024-07-20 | 2025-07-22 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
804 K285 K
Llama-3.1-405B-FP8
Qwen3-Coder-480B-A35B-Instruct-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.1-405B-FP8 · fp16
597.3 GB / 24 GB
Qwen3-Coder-480B-A35B-Instruct-FP8 · fp16 @ 256K ctx
2,835.7 GB / 24 GB