NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 vs DeepSeek-V4-Flash-DSpark

Specs, VRAM requirements and download trends — updated 6 August 2026.

nvidia · A
Params
67.2 B
Context
262,144
30d
2.8 M
deepseek-ai · B
Params
165.3 B
Context
1,048,576
30d
519 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 DeepSeek-V4-Flash-DSpark
Parameters 67.2 B 165.3 B
Architecture NemotronHForCausalLM DeepseekV4ForCausalLM
Context length 262,144 1,048,576
Licence other mit
Commercial use Unknown Allowed
Languages 7
Downloads 30d 2,830,012 519,483
Downloads all time 8.3 M 597 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-03-10 2026-06-27

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

3.1 M442 K
NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 DeepSeek-V4-Flash-DSpark

VRAM side by side

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

NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 · fp16 @ 256K ctx 411.6 GB / 24 GB
❌ Won’t fit
DeepSeek-V4-Flash-DSpark · fp16 @ 1024K ctx 3,357.3 GB / 24 GB
❌ Won’t fit

Adjacent comparisons