MiniMax-M2.7 vs Qwen3.5-122B-A10B-NVFP4
Specs, VRAM requirements and download trends — updated 27 September 2026.
nvidia · B · Open weights
Params
64.6 B
Context
—
30d
351 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | MiniMax-M2.7 | Qwen3.5-122B-A10B-NVFP4 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 228.7 B | 64.6 B |
| Architecture | MiniMaxM2ForCausalLM | Qwen3_5MoeForConditionalGeneration |
| Context length | 204,800 | — |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 438,954 | 351,083 |
| Downloads all time | 7.9 M | 2.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-09 | 2026-05-13 |
| API input price / 1M tokens | $0.30 | not on OpenRouter |
| API output price / 1M tokens | $1.20 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $1.50 | not on OpenRouter |
| Cached input / 1M tokens | $0.06 | not on OpenRouter |
| AA Intelligence Index | 22.8 | not on OpenRouter |
| AA Coding Index | 52.6 | not on OpenRouter |
| AA Agentic Index | 15.3 | not on OpenRouter |
| Max output tokens | 131,072 | not on OpenRouter |
| API providers | 5 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
MiniMax-M2.7
$1.50
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.5 M241 K
MiniMax-M2.7
Qwen3.5-122B-A10B-NVFP4
A overtook B on 19 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.5-122B-A10B-NVFP4 · fp16
102.0 GB / 24 GB
MiniMax-M2.7 · fp16 @ 200K ctx
1,111.3 GB / 24 GB
Adjacent comparisons
MiniMax-M2.7 vs DeepSeek-V4-Flash-0731
Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF vs Qwen3.5-122B-A10B-NVFP4
Qwen2.5-Coder-32B-Instruct vs Qwen3.5-122B-A10B-NVFP4
dolphin-2.9.1-yi-1.5-34b vs Qwen3.5-122B-A10B-NVFP4
Qwen2.5-Coder-32B-Instruct-AWQ vs Qwen3.5-122B-A10B-NVFP4
DeepSeek-V3.2 vs MiniMax-M2.7