Can I Run GLM-4.7 / GLM-Z1 on NVIDIA L40S?
Written by Jakub Rusinowski · Last updated August 15, 2026
Yes, comfortably — GLM-Z1 32B (Reasoning) at Q4_K_M needs 22 GB at 8K context (19.3 GB weights + 2.7 GB KV cache/overhead), leaving ~26 GB of the NVIDIA L40S's 48 GB, at ~36 tok/s (est.), with room for up to 64K context.
See what else this hardware can run →
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
NVIDIA L40S Specs
| VRAM | 48 GB |
| Memory Bandwidth | 864 GB/s |
GLM-Z1 32B (Reasoning) on the NVIDIA L40S: VRAM by quantization
| Quant | VRAM needed | Fits 48 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 66.6 GB | ✗ No | — | — |
| Q8_0 | 36.6 GB | ✓ Yes | 32K | Build for this |
| Q6_K | 28.9 GB | ✓ Yes | 64K | — |
| Q5_K_M | 25.3 GB | ✓ Yes | 64K | — |
| Q4_K_M | 22 GB | ✓ Yes | 64K | Build for this |
| Q3_K_M | 16.3 GB | ✓ Yes | 64K | — |
| Q2_K | 13.2 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 48 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA L40S: 8K 22 GB · 32K 27.5 GB · 125K 49 GB ✗. Past 125K it no longer fits 48 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? GLM-Z1 32B (Reasoning) on 32 GB of system RAM, CPU only: runs comfortably.
GLM-4.7 / GLM-Z1 Sizes That Fit the NVIDIA L40S (at 8K context)
| GLM-Z1 32B (Reasoning) | Q4_K_M · 22 GB at 8K context · ~36 tok/s (est.) |
| GLM-4.7-Flash 30B-A3B | Q4_K_M · 20.7 GB at 8K context · ~178 tok/s (est.) |
| GLM-4 9B | Q4_K_M · 7.4 GB at 8K context · ~102 tok/s (est.) |
At 2 hrs/day, buying (~$7,499) beats renting at $0.34/hr after about 30.6 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the NVIDIA L40S enough to run GLM-4.7 / GLM-Z1 locally?
Yes, comfortably — GLM-Z1 32B (Reasoning) at Q4_K_M needs 22 GB at 8K context (19.3 GB weights + 2.7 GB KV cache/overhead), leaving ~26 GB of the NVIDIA L40S's 48 GB, at ~36 tok/s (est.), with room for up to 64K context.
What's the best GLM-4.7 / GLM-Z1 size for the NVIDIA L40S?
GLM-Z1 32B (Reasoning) at Q4_K_M quantization needs 22 GB at 8K context (19.3 GB weights + 2.7 GB KV cache/overhead), estimated ~36 tokens/sec, up to 64K context.
Every GLM-4.7 / GLM-Z1 size on the NVIDIA L40S
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| GLM-Z1 32B (Reasoning) | 22 GB | Runs | ~36 tok/s |
| GLM-4.7-Flash 30B-A3B | 20.7 GB | Runs | ~178 tok/s |
| GLM-4 9B | 7.4 GB | Runs | ~102 tok/s |
GLM-4.7 / GLM-Z1 on Other GPUs
- GLM-4.7 / GLM-Z1 on NVIDIA RTX 6000 Ada Generation
- GLM-4.7 / GLM-Z1 on Apple M3 Pro
- GLM-4.7 / GLM-Z1 on NVIDIA GeForce RTX 5090
- GLM-4.7 / GLM-Z1 on Apple M4
- GLM-4.7 / GLM-Z1 on Apple M2 Pro
Popular Models on the NVIDIA L40S
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | GLM-4.7 / GLM-Z1 Model Page | NVIDIA L40S GPU Page | VRAM calculator | Check Your Hardware