TinyLlama 1.1B
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Parameters
1.1B
Context
2K
Downloads
2.3M
Likes
1.7K
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 7.5 GB RAM 32.0 · Disk 42.2 | 23.4 GB RAM 35.1 · Disk 68.2 | 120.4 GB RAM 180.6 · Disk 107.2 |
| FP88bit | 6.3 GB RAM 32.0 · Disk 40.6 | 22.1 GB RAM 33.1 · Disk 66.6 | 119.0 GB RAM 178.5 · Disk 105.6 |
| INT88bit | 6.3 GB RAM 32.0 · Disk 40.6 | 22.1 GB RAM 33.1 · Disk 66.6 | 119.0 GB RAM 178.5 · Disk 105.6 |
| AWQ4bit | 5.6 GB RAM 32.0 · Disk 39.8 | 21.4 GB RAM 32.1 · Disk 65.8 | 118.3 GB RAM 177.5 · Disk 104.8 |
| GPTQ4bit | 5.6 GB RAM 32.0 · Disk 39.8 | 21.4 GB RAM 32.1 · Disk 65.8 | 118.3 GB RAM 177.5 · Disk 104.8 |
| GGUF4bit | 5.7 GB RAM 32.0 · Disk 39.9 | 21.4 GB RAM 32.1 · Disk 65.9 | 118.4 GB RAM 177.5 · Disk 104.9 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 3381.1 tok/s
Effective production throughput ≈ 2366.8 tok/s
score 0.6779
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6243
8× H200 SXM
1128 GB VRAM
≈ 28981.1 tok/s
Effective production throughput ≈ 20286.8 tok/s
score 0.2197
1× L4
24 GB VRAM
≈ 566 tok/s
Effective production throughput ≈ 396.2 tok/s
score 0.6528
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
L4
24 GB VRAM
$76.2
/mo · vast
RTX 3090
24 GB VRAM
$79.6
/mo · vast
RTX 5090
32 GB VRAM
$155
/mo · vast
A10
24 GB VRAM
$177
/mo · vast
RTX 4090
24 GB VRAM
$190
/mo · tensordock