OLMo 3.1 32B
allenai/Olmo-3.1-32B-Instruct
Parameters
32B
Context
64K
Downloads
54.5K
Likes
82
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 80.4 GB RAM 120.5 · Disk 132.0 | 99.5 GB RAM 149.3 · Disk 158.0 | 199.9 GB RAM 299.8 · Disk 197.0 |
| FP88bit | 42.7 GB RAM 64.0 · Disk 85.5 | 60.1 GB RAM 90.2 · Disk 111.5 | 158.7 GB RAM 238.1 · Disk 150.5 |
| INT88bit | 42.7 GB RAM 64.0 · Disk 85.5 | 60.1 GB RAM 90.2 · Disk 111.5 | 158.7 GB RAM 238.1 · Disk 150.5 |
| AWQ4bit | 24.5 GB RAM 36.8 · Disk 63.1 | 41.2 GB RAM 61.7 · Disk 89.1 | 138.9 GB RAM 208.4 · Disk 128.1 |
| GPTQ4bit | 24.7 GB RAM 37.1 · Disk 63.4 | 41.4 GB RAM 62.1 · Disk 89.4 | 139.2 GB RAM 208.8 · Disk 128.4 |
| GGUF4bit | 25.2 GB RAM 37.8 · Disk 64.0 | 41.9 GB RAM 62.8 · Disk 90.0 | 139.7 GB RAM 209.6 · Disk 129.0 |
GPU Recommendations
1× H100 SXM
80 GB VRAM
≈ 216.7 tok/s
Effective production throughput ≈ 151.7 tok/s
score 0.6267
4× Tesla V100
64 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5698
8× H200 SXM
1128 GB VRAM
≈ 993.5 tok/s
Effective production throughput ≈ 695.4 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 49.7 tok/s
Effective production throughput ≈ 34.8 tok/s
score 0.6625
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX A6000
48 GB VRAM
$210
/mo · vast
L40S
48 GB VRAM
$341
/mo · vast
RTX PRO 6000 WS
48 GB VRAM
$482
/mo · vast
RTX PRO 6000 S
48 GB VRAM
$633
/mo · vast
A100 80GB
80 GB VRAM
$876
/mo · vast