Can I Run GLM-5 / GLM-5.1 on NVIDIA L40S?
Written by Jakub Rusinowski · Last updated July 21, 2026
Yes, but it's tight — GLM-5.1 72B at Q4_K_M needs 46.7 GB at 8K context (43.5 GB weights + 3.2 GB KV cache/overhead), leaving ~1.3 GB of the NVIDIA L40S's 48 GB, at ~17 tok/s (est.), with room for up to 8K 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-5.1 72B on the NVIDIA L40S: VRAM by quantization
| Quant | VRAM needed | Fits 48 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 147.2 GB | ✗ No | — | — |
| Q8_0 | 79.7 GB | ✗ No | — | — |
| Q6_K | 62.3 GB | ✗ No | — | — |
| Q5_K_M | 54.2 GB | ✗ No | — | — |
| Q4_K_M | 46.7 GB | ✓ Yes | 8K | — |
| Q3_K_M | 33.9 GB | ✓ Yes | 32K | — |
| Q2_K | 26.9 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 46.7 GB · 32K 53.9 GB ✗ · 125K 82 GB ✗. Past 32K 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-5 / GLM-5.1 on 8 GB of system RAM, CPU only: runs, but it is tight.
GLM-5 / GLM-5.1 Sizes That Fit the NVIDIA L40S (at 8K context)
| GLM-5.1 72B | Q4_K_M · 46.7 GB at 8K context · ~17 tok/s (est.) |
| GLM-5 32B | Q4_K_M · 22 GB at 8K context · ~36 tok/s (est.) |
| GLM-5 9B | Q4_K_M · 7.4 GB at 8K context · ~102 tok/s (est.) |
At 2 hrs/day, buying (~$7,499) beats renting at $0.77/hr after about 13.5 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
Can I run GLM-5 / GLM-5.1 on the NVIDIA L40S?
Yes, but it's tight — GLM-5.1 72B at Q4_K_M needs 46.7 GB at 8K context (43.5 GB weights + 3.2 GB KV cache/overhead), leaving ~1.3 GB of the NVIDIA L40S's 48 GB, at ~17 tok/s (est.), with room for up to 8K context.
What's the best GLM-5 / GLM-5.1 size for the NVIDIA L40S?
GLM-5.1 72B at Q4_K_M quantization needs 46.7 GB at 8K context (43.5 GB weights + 3.2 GB KV cache/overhead), estimated ~17 tokens/sec, up to 8K context.
Every GLM-5 / GLM-5.1 size on the NVIDIA L40S
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| GLM-5 744B | 455.2 GB | Does not fit | — |
| GLM-5.1 72B | 46.7 GB | Runs | ~17 tok/s |
| GLM-5 32B | 22 GB | Runs | ~36 tok/s |
| GLM-5 9B | 7.4 GB | Runs | ~102 tok/s |
GLM-5 / GLM-5.1 on Other GPUs
- GLM-5 / GLM-5.1 on NVIDIA RTX 6000 Ada Generation
- GLM-5 / GLM-5.1 on Apple M3 Pro
- GLM-5 / GLM-5.1 on NVIDIA GeForce RTX 5090
- GLM-5 / GLM-5.1 on Apple M4
- GLM-5 / GLM-5.1 on Apple M2 Pro
Popular Models on the NVIDIA L40S
VRAM Tier
Troubleshooting
- CUDA out of memory — why it happens and how to fix it
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | GLM-5 / GLM-5.1 Model Page | NVIDIA L40S GPU Page | Check Your Hardware