DeepSeek-V4-Flash-0731 vs Llama-3.1-405B-FP8

Specs, VRAM requirements and download trends — updated 21 September 2026.

deepseek-ai · A
Params
304.2 B
Context
1,048,576
30d
4.1 M
mit · commercial OK
meta-llama · B
Params
405.9 B
Context
30d
465 K
llama3.1 licence · conditional

Specification comparison

Differences are highlighted; identical values are muted.

Specification DeepSeek-V4-Flash-0731 Llama-3.1-405B-FP8
Parameters 304.2 B 405.9 B
Architecture DeepseekV4ForCausalLM LlamaForCausalLM
Context length 1,048,576
Licence mit llama3.1
Commercial use Allowed Conditional
Languages 8
Downloads 30d 4,086,610 465,220
Downloads all time 7.0 M 1.9 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No Yes — accept licence
First seen on the Hub 2026-07-31 2024-07-20

Download trend

Daily snapshots, last 49 days (4 Aug – 21 Sep)

4.7 M236 K
DeepSeek-V4-Flash-0731 Llama-3.1-405B-FP8 A overtook B on 7 Aug

VRAM side by side

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

Llama-3.1-405B-FP8 · fp16 597.3 GB / 24 GB
❌ Won’t fit
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx 6,024.3 GB / 24 GB
❌ Won’t fit

Adjacent comparisons