GPUs & Macs › NVIDIA A40-48Q
NVIDIA A40-48Q: local LLM speed
1 measured result for the NVIDIA A40-48Q.
Measured results
| Model | Generate tok/s | Prompt tok/s | Quant | Backend | Test | Source |
|---|---|---|---|---|---|---|
| Qwen2.5 14B Instruct | 39.5 | 1,707 | Q4_K_M | llamafile | LocalScore avg | LocalScore details |
What fits on the NVIDIA A40-48Q
Estimates for this chip are scaled from a measured run: Qwen2.5 14B Instruct Q4_K_M at 39.5 tok/s (llamafile, source). Fit assumes the whole model in GPU memory with ~8K context.
| Model | Best quant that fits | File | Expected tok/s |
|---|---|---|---|
| Qwen3.8-27B | Q8_0 | 29.0 GB | 12.2 estimate |
| gemma-4-12B-it | Q8_0 | 12.7 GB | 28.0 estimate |
| Qwen3.5-9B | Q8_0 | 9.5 GB | 37.3 estimate |
| Qwen3.5-4B | Q8_0 | 4.5 GB | 79.2 estimate |
| Qwen3.6-35B-A3B | Q8_0 | 36.9 GB | 56.2 estimate |
| gemma-4-26B-A4B-it | Q8_0 | 26.9 GB | 43.0 estimate |
| MiMo-V2.6-Distill-Qwen-9B | Q8_0 | 9.5 GB | 37.2 estimate |
| gemma-4-E4B-it | Q8_0 | 8.2 GB | 43.4 estimate |
| Muse-Glimmer-30B | Q8_0 | 29.6 GB | 12.0 estimate |
| Qwen3-4B | Q8_0 | 4.3 GB | 83.0 estimate |
| gemma-4-31B-it | Q8_0 | 32.6 GB | 10.9 estimate |
| gemma-4-26B-A4B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 14.2 GB | 81.0 estimate |
| gemma-4-12B-it-qat-q4_0-unquantized | UD-Q4_K_XL | 6.7 GB | 52.9 estimate |
| gemma-3-1b-it | Q8_0 | 1.1 GB | 296 estimate |
Similar hardware
NVIDIA RTX 5090 · NVIDIA RTX 4090 D · NVIDIA RTX 4090 · NVIDIA RTX 3090 Ti · NVIDIA RTX 3090 · NVIDIA TITAN RTX · NVIDIA Quadro P6000 · NVIDIA RTX 5080