GLM-4.7-Flash
zai-org/GLM-4.7-Flash
Parameters
30B
Context
128K
Downloads
1.9M
Likes
1.8K
Architecture
moe_transformer
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 75.6 GB RAM 113.5 · Disk 126.2 | 94.6 GB RAM 141.9 · Disk 152.2 | 194.7 GB RAM 292.1 · Disk 191.2 |
| FP88bit | 40.3 GB RAM 60.4 · Disk 82.6 | 57.7 GB RAM 86.5 · Disk 108.6 | 156.2 GB RAM 234.2 · Disk 147.6 |
| INT88bit | 40.3 GB RAM 60.4 · Disk 82.6 | 57.7 GB RAM 86.5 · Disk 108.6 | 156.2 GB RAM 234.2 · Disk 147.6 |
| AWQ4bit | 23.3 GB RAM 34.9 · Disk 61.6 | 39.9 GB RAM 59.8 · Disk 87.6 | 137.6 GB RAM 206.4 · Disk 126.6 |
| GPTQ4bit | 23.5 GB RAM 35.3 · Disk 61.9 | 40.1 GB RAM 60.2 · Disk 87.9 | 137.8 GB RAM 206.8 · Disk 126.9 |
| GGUF4bit | 24.0 GB RAM 35.9 · Disk 62.4 | 40.6 GB RAM 60.8 · Disk 88.4 | 138.3 GB RAM 207.5 · Disk 127.4 |
GPU Recommendations
1× H100 SXM
80 GB VRAM
≈ 231.2 tok/s
Effective production throughput ≈ 161.8 tok/s
score 0.6225
4× Tesla V100
64 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5644
8× H200 SXM
1128 GB VRAM
≈ 1060 tok/s
Effective production throughput ≈ 742 tok/s
score 0.2197
1× RTX A6000
48 GB VRAM
≈ 53 tok/s
Effective production throughput ≈ 37.1 tok/s
score 0.6696
💬 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