MiniMax-M2.7 vs NVIDIA-Nemotron-3-Super-120B-A12B-BF16

Specs, VRAM requirements and download trends — updated 9 September 2026.

MiniMaxAI · A
Params
228.7 B
Context
204,800
30d
1.3 M
nvidia · B
Params
123.6 B
Context
262,144
30d
1.2 M

Specification comparison

Differences are highlighted; identical values are muted.

Specification MiniMax-M2.7 NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Parameters 228.7 B 123.6 B
Architecture MiniMaxM2ForCausalLM NemotronHForCausalLM
Context length 204,800 262,144
Licence other other
Commercial use Unknown Unknown
Languages 7
Downloads 30d 1,267,597 1,188,842
Downloads all time 6.8 M 5.5 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-09 2026-03-10

Download trend

Daily snapshots, last 44 days (28 Jul – 9 Sep)

1.3 M812 K
MiniMax-M2.7 NVIDIA-Nemotron-3-Super-120B-A12B-BF16 A overtook B on 27 Aug

VRAM side by side

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

NVIDIA-Nemotron-3-Super-120B-A12B-BF16 · fp16 @ 256K ctx 865.8 GB / 24 GB
❌ Won’t fit
MiniMax-M2.7 · fp16 @ 200K ctx 1,111.3 GB / 24 GB
❌ Won’t fit

Adjacent comparisons