Can GLM Z1 32B 0414 run on the L40S?
Yes. At 8K context the best fit is Q8_0, using about 33.4 GB of the 45.6 GB usable on the L40S. Estimated speed ceiling: ~25 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 12.3 GB Fits | 12.5 GB Fits | 14.0 GB Fits | 71 |
| 3-bit (Q3_K_M) | 15.8 GB Fits | 16.0 GB Fits | 17.4 GB Fits | 54 |
| 4-bit (Q4_K_M) • | 19.3 GB Fits | 19.5 GB Fits | 20.9 GB Fits | 44 |
| 5-bit (Q5_K_M) | 22.5 GB Fits | 22.8 GB Fits | 24.2 GB Fits | 37 |
| 6-bit (Q6_K) • | 25.8 GB Fits | 26.1 GB Fits | 27.5 GB Fits | 32 |
| 8-bit (Q8_0) • | 33.2 GB Fits | 33.4 GB Fits | 34.8 GB Fits | 25 |
| 16-bit (F16/BF16) | 61.6 GB No | 61.8 GB No | 63.3 GB No | — |
• real GGUF file size from lmstudio-community/GLM-Z1-32B-0414-GGUF. Speed is a bandwidth ceiling (864 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs GLM Z1 32B 0414: RX 7900 XTX (24 GB, launch MSRP $999) at Q4_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the L40S: Qwen3.6 35B A3B (36B, MoE) at Q8_0, about 36.2 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
GLM Z1 32B 0414 on every GPU and Mac · Every model that runs on the L40S · Other models that fit 48 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (zai-org/GLM-Z1-32B-0414), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.