DeepSeek-V3.2 vs Ornith-1.0-397B-FP8

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

deepseek-ai · A
Params
685.4 B
Context
163,840
30d
2.5 M
mit · commercial OK
deepreinforce-ai · B
Params
397.0 B
Context
30d
673 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification DeepSeek-V3.2 Ornith-1.0-397B-FP8
Parameters 685.4 B 397.0 B
Architecture DeepseekV32ForCausalLM Qwen3_5MoeForConditionalGeneration
Context length 163,840
Licence mit mit
Commercial use Allowed Allowed
Languages
Downloads 30d 2,488,767 672,806
Downloads all time 24.5 M 771 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-12-01 2026-06-25

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

2.5 M631 K
DeepSeek-V3.2 Ornith-1.0-397B-FP8

VRAM side by side

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

Ornith-1.0-397B-FP8 · fp16 505.7 GB / 24 GB
❌ Won’t fit
DeepSeek-V3.2 · fp16 @ 160K ctx 2,815.1 GB / 24 GB
❌ Won’t fit

Adjacent comparisons