MiniMax-M1-80B
MiniMaxAI/MiniMax-M1-80B
MiniMax M1, 80B reasoning model with strong coding benchmarks.
Parameters
80B
Context
128K
Downloads
180K
Likes
900
Architecture
llama
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 193.5 GB RAM 290.2 · Disk 271.5 | 217.8 GB RAM 326.7 · Disk 297.5 | 323.2 GB RAM 484.9 · Disk 336.5 |
| FP88bit | 99.2 GB RAM 148.8 · Disk 155.2 | 119.2 GB RAM 178.9 · Disk 181.2 | 220.4 GB RAM 330.6 · Disk 220.2 |
| INT88bit | 99.2 GB RAM 148.8 · Disk 155.2 | 119.2 GB RAM 178.9 · Disk 181.2 | 220.4 GB RAM 330.6 · Disk 220.2 |
| AWQ4bit | 53.8 GB RAM 80.8 · Disk 99.3 | 71.8 GB RAM 107.7 · Disk 125.3 | 170.9 GB RAM 256.4 · Disk 164.3 |
| GPTQ4bit | 54.4 GB RAM 81.7 · Disk 100.0 | 72.4 GB RAM 108.7 · Disk 126.0 | 171.6 GB RAM 257.4 · Disk 165.0 |
| GGUF4bit | 55.6 GB RAM 83.4 · Disk 101.5 | 73.7 GB RAM 110.5 · Disk 127.5 | 172.9 GB RAM 259.3 · Disk 166.5 |
GPU Recommendations
1× H200 SXM
141 GB VRAM
≈ 124.2 tok/s
Effective production throughput ≈ 86.9 tok/s
score 0.6069
8× Tesla V100
128 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5061
8× H200 SXM
1128 GB VRAM
≈ 397.4 tok/s
Effective production throughput ≈ 278.2 tok/s
score 0.2197
1× A100 80GB
80 GB VRAM
≈ 52.8 tok/s
Effective production throughput ≈ 37 tok/s
score 0.6469
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
A100 80GB
80 GB VRAM
$876
/mo · vast
H100 SXM
80 GB VRAM
$1,170
/mo · vast
H200 SXM
141 GB VRAM
$2,555
/mo · lambda
B200
180 GB VRAM
$3,013
/mo · vast
B200 SXM
180 GB VRAM
—