Can I Run GLM-4.7-Flash 30B-A3B on NVIDIA L40S?
Written by Jakub Rusinowski · Last updated August 15, 2026
Yes. GLM-4.7-Flash 30B-A3B needs 20.7 GB at 8K context (18.1 GB weights + 2.6 GB KV cache/overhead) at Q4_K_M and the NVIDIA L40S has 48 GB, leaving about 27.3 GB of headroom, at roughly 178 tok/s (estimated) with room for up to 128K of context.
See what else this hardware can run →
The numbers
| Model | GLM-4.7-Flash 30B-A3B |
| Parameters | 30B (3B active) |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 20.7 GB |
| NVIDIA L40S VRAM | 48 GB |
| Verdict | Runs |
| Max context | 128K |
| Estimated speed | ~178 tok/s |
GLM-4.7-Flash 30B-A3B on the NVIDIA L40S: VRAM by quantization
| Quant | VRAM needed | Fits 48 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 62.6 GB | ✗ No | — | — |
| Q8_0 | 34.5 GB | ✓ Yes | 64K | Build for this |
| Q6_K | 27.2 GB | ✓ Yes | 64K | — |
| Q5_K_M | 23.8 GB | ✓ Yes | 64K | Build for this |
| Q4_K_M | 20.7 GB | ✓ Yes | 128K | Build for this |
| Q3_K_M | 15.4 GB | ✓ Yes | 128K | — |
| Q2_K | 12.4 GB | ✓ Yes | 128K | — |
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 20.7 GB · 32K 26 GB · 128K 47.4 GB. Every window this model publishes still fits 48 GB.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? GLM-4.7 / GLM-Z1 on 8 GB of system RAM, CPU only: runs, but it is tight.
Running GLM-4.7-Flash 30B-A3B on this card:
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.
Other GLM-4.7 / GLM-Z1 sizes on the NVIDIA L40S
- GLM-Z1 32B (Reasoning) — runs (22 GB)
- GLM-4 9B — runs (7.4 GB)
GLM-4.7-Flash 30B-A3B on nearby hardware
- Apple M3 Pro (36 GB) — runs
All GLM-4.7 / GLM-Z1 sizes on the NVIDIA L40S | GLM-4.7-Flash 30B-A3B model page | NVIDIA L40S GPU page | VRAM calculator | Check your hardware