ChatGLM2 6B
THUDM/chatglm2-6b
Parameters
6B
Context
32K
Downloads
420.9K
Likes
2.1K
Architecture
transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 19.1 GB RAM 32.0 · Disk 56.4 | 35.5 GB RAM 53.2 · Disk 82.4 | 133.0 GB RAM 199.5 · Disk 121.4 |
| FP88bit | 12.0 GB RAM 32.0 · Disk 47.7 | 28.1 GB RAM 42.1 · Disk 73.7 | 125.3 GB RAM 188.0 · Disk 112.7 |
| INT88bit | 12.0 GB RAM 32.0 · Disk 47.7 | 28.1 GB RAM 42.1 · Disk 73.7 | 125.3 GB RAM 188.0 · Disk 112.7 |
| AWQ4bit | 8.6 GB RAM 32.0 · Disk 43.5 | 24.5 GB RAM 36.8 · Disk 69.5 | 121.6 GB RAM 182.4 · Disk 108.5 |
| GPTQ4bit | 8.7 GB RAM 32.0 · Disk 43.6 | 24.6 GB RAM 36.9 · Disk 69.6 | 121.7 GB RAM 182.5 · Disk 108.6 |
| GGUF4bit | 8.8 GB RAM 32.0 · Disk 43.7 | 24.7 GB RAM 37.0 · Disk 69.7 | 121.7 GB RAM 182.6 · Disk 108.7 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 617.9 tok/s
Effective production throughput ≈ 432.5 tok/s
score 0.6935
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6422
8× H200 SXM
1128 GB VRAM
≈ 5296.6 tok/s
Effective production throughput ≈ 3707.6 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 264.8 tok/s
Effective production throughput ≈ 185.4 tok/s
score 0.6274
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX A6000
48 GB VRAM
$210
/mo · vast
RTX 5090
32 GB VRAM
$236
/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