M2M100-1.2B
facebook/m2m100-1.2B
Meta M2M100 multilingual translation.
Parameters
1.2B
Context
1K
Downloads
310K
Likes
500
Architecture
m2m100
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 7.8 GB RAM 32.0 · Disk 42.5 | 23.7 GB RAM 35.5 · Disk 68.5 | 120.7 GB RAM 181.0 · Disk 107.5 |
| FP88bit | 6.4 GB RAM 32.0 · Disk 40.7 | 22.2 GB RAM 33.3 · Disk 66.7 | 119.1 GB RAM 178.7 · Disk 105.7 |
| INT88bit | 6.4 GB RAM 32.0 · Disk 40.7 | 22.2 GB RAM 33.3 · Disk 66.7 | 119.1 GB RAM 178.7 · Disk 105.7 |
| AWQ4bit | 5.7 GB RAM 32.0 · Disk 39.9 | 21.5 GB RAM 32.2 · Disk 65.9 | 118.4 GB RAM 177.6 · Disk 104.9 |
| GPTQ4bit | 5.7 GB RAM 32.0 · Disk 39.9 | 21.5 GB RAM 32.2 · Disk 65.9 | 118.4 GB RAM 177.6 · Disk 104.9 |
| GGUF4bit | 5.7 GB RAM 32.0 · Disk 39.9 | 21.5 GB RAM 32.2 · Disk 65.9 | 118.4 GB RAM 177.6 · Disk 104.9 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 3089.7 tok/s
Effective production throughput ≈ 2162.8 tok/s
score 0.675
1× RTX 3090
24 GB VRAM
≈ 1613.8 tok/s
Effective production throughput ≈ 1129.7 tok/s
score 0.6563
8× H200 SXM
1128 GB VRAM
≈ 26482.8 tok/s
Effective production throughput ≈ 18538 tok/s
score 0.2197
1× RTX 4090
24 GB VRAM
≈ 1737.9 tok/s
Effective production throughput ≈ 1216.5 tok/s
score 0.6547
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3090
24 GB VRAM
$88.4
/mo · vast
A10
24 GB VRAM
$171
/mo · vast
L4
24 GB VRAM
$185
/mo · vast
RTX 4090
24 GB VRAM
$190
/mo · tensordock
RTX A6000
48 GB VRAM
$264
/mo · vast