Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
32.5 tok/s
TTFT
5958 ms
Safe context
4K
Memory
32.1 GB / 48.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 32.5 tok/s | 8666 ms | 4K |
| Chat | C | Runs well | 32.5 tok/s | 3250 ms | 4K |
| Coding | C | Runs well | 32.5 tok/s | 5958 ms | 4K |
| RAG | C | Runs well | 32.5 tok/s | 10833 ms | 4K |
| Reasoning | C | Runs well | 32.5 tok/s | 7041 ms | 4K |
How Yi 1.5 34B (34B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.3 GB | Low | D35 |
Q3_K_S | 3 | 16.7 GB | Low | D37 |
NVFP4 | 4 | 19.0 GB | Medium | D38 |
Q4_K_M | 4 | 20.7 GB | Medium | D38 |
Q5_K_M | 5 | 24.5 GB | High | C40 |
Q6_K | 6 | 27.9 GB | High | C42 |
Q8_0Best for your GPU | 8 | 36.4 GB | Very High | C44 |
F16 | 16 | 69.7 GB | Maximum | F0 |
ollama run yi-1.5-34bhuggingface-cli download yi-1.5-34b