NVIDIA CMP 170HX 40GB (unlocked) vs NVIDIA Tesla P40 24GB for local LLMs
3 reports on the NVIDIA CMP 170HX 40GB (unlocked) and 8 on the NVIDIA Tesla P40 24GB
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 4.3x higher on the NVIDIA CMP 170HX 40GB (unlocked) (1,493 GB/s on the NVIDIA CMP 170HX 40GB (unlocked), 346 on the NVIDIA Tesla P40 24GB). The estimates below compare them on the models people run most.
- Memory
- 40GB
- Memory bandwidth
- 1,493 GB/s
- FP16 compute
- not on record
- Reports
- 3
- Memory
- 24GB
- Memory bandwidth
- 346 GB/s
- FP16 compute
- 12 TFLOPS
- Reports
- 8
Estimated by the calculator
The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape.
| Model | NVIDIA CMP 170HX 40GB (unlocked) | NVIDIA Tesla P40 24GB |
|---|---|---|
| Qwen3.8 27B | 30.4 t/sQ8_0 | 12.5 t/sQ4_K_M |
| Qwen3.8 125B · 6B active | 16.8 t/sQ3_K_S, experts in RAM | 16.9 t/sQ2_K, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 120.3 t/sQ6_K | 44.4 t/sQ4_K_S |
| Qwen3.6 27B | 30.4 t/sQ8_0 | 12.5 t/sQ4_K_M |
| Gemma 4 26B · 4B active | 78.3 t/sQ8_0 | 28.2 t/sQ5_K_S |
Change the context, RAM or model in the calculator: NVIDIA CMP 170HX 40GB (unlocked) · NVIDIA Tesla P40 24GB
Every report on each card, with its source: NVIDIA CMP 170HX 40GB (unlocked) · NVIDIA Tesla P40 24GB