OLMo 3 7B
allenai/Olmo-3-7B-Instruct
Parameters
7B
Context
64K
Downloads
425.4K
Likes
141
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 21.4 GB RAM 32.2 · Disk 59.3 | 37.9 GB RAM 56.9 · Disk 85.3 | 135.6 GB RAM 203.4 · Disk 124.3 |
| FP88bit | 13.2 GB RAM 32.0 · Disk 49.2 | 29.3 GB RAM 44.0 · Disk 75.2 | 126.6 GB RAM 189.9 · Disk 114.2 |
| INT88bit | 13.2 GB RAM 32.0 · Disk 49.2 | 29.3 GB RAM 44.0 · Disk 75.2 | 126.6 GB RAM 189.9 · Disk 114.2 |
| AWQ4bit | 9.2 GB RAM 32.0 · Disk 44.3 | 25.2 GB RAM 37.8 · Disk 70.3 | 122.3 GB RAM 183.4 · Disk 109.3 |
| GPTQ4bit | 9.3 GB RAM 32.0 · Disk 44.3 | 25.2 GB RAM 37.8 · Disk 70.3 | 122.3 GB RAM 183.5 · Disk 109.3 |
| GGUF4bit | 9.4 GB RAM 32.0 · Disk 44.5 | 25.3 GB RAM 38.0 · Disk 70.5 | 122.4 GB RAM 183.7 · Disk 109.5 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 530.2 tok/s
Effective production throughput ≈ 371.1 tok/s
score 0.6863
2× RTX 3090
48 GB VRAM
≈ 443.1 tok/s
Effective production throughput ≈ 310.2 tok/s
score 0.5943
8× H200 SXM
1128 GB VRAM
≈ 4544.4 tok/s
Effective production throughput ≈ 3181.1 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 227.2 tok/s
Effective production throughput ≈ 159 tok/s
score 0.6298
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX A6000
48 GB VRAM
$265
/mo · vast
RTX 5090D
32 GB VRAM
$294
/mo · vast
RTX 5090
32 GB VRAM
$325
/mo · vast
L40S
48 GB VRAM
$341
/mo · vast
A100 PCIE
80 GB VRAM
$390
/mo · vast