Can the Tesla P40 run Darwin-27B-RSI?
Darwin-27B-RSI·26.9B·Tesla P40·24 GB VRAM
Yes. The Tesla P40 runs Darwin-27B-RSI fully in VRAM at Q5_K_M (about 23 GB of 24 GB), at roughly 10 tokens/s.
- best quant
- Q5_K_M
- needs
- 23 GB
- usable
- 24 GB
- est. speed
- ~10 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Darwin-27B-RSI page →
Every quantisation of Darwin-27B-RSI on the Tesla P40
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 13 GB | fits | ~22 tok/s |
| Q3_K_M | 15 GB | fits | ~15 tok/s |
| Q4_K_M | 19 GB | fits | ~12 tok/s |
| Q5_K_M pick | 23 GB | fits | ~10 tok/s |
| Q6_K | 26 GB | offload | ~6.6 tok/s |
| Q8_0 | 31 GB | offload | ~3.3 tok/s |
| FP16 / BF16 | 55 GB | too big | — |
Speed is a bandwidth-based estimate for generating text (347 GB/s); prompt processing and long contexts are slower.
Measured speed on the Tesla P40
No community reports for this pair yet.
Report your own speed →Run Darwin-27B-RSI on the Tesla P40
Using Q5_K_M, the best fit for Tesla P40.
ollama run hf.co/bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF:Q5_K_M llama-server -hf bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF:Q5_K_MDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get bartowski/FINAL-Bench_Darwin-27B-RSI-GGUF@Q5_K_MThen load it from the LM Studio app or with `lms load`.
vllm serve FINAL-Bench/Darwin-27B-RSIservices:
vllm:
image: vllm/vllm-openai:latest
command: FINAL-Bench/Darwin-27B-RSI
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve FINAL-Bench/Darwin-27B-RSI --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve FINAL-Bench/Darwin-27B-RSI --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
from transformers import pipeline
pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-27B-RSI", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])Chat models that fit the Tesla P40 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 20.9BA4.2B | Q8_0 | ≈13 GBFits in memory | ~43 tok/s | |
| 32.8B | Q4_K_M | ≈22 GBFits in memory | ~9.6 tok/s | |
| 36BA3B | Q4_K_M | ≈23 GBFits in memory | ~105 tok/s | |
| 30.5BA3B | Q5_K_M | ≈22 GBFits in memory | ~89 tok/s | |
| 24BA2B | Q6_K | ≈20 GBFits in memory | ~116 tok/s | |
| 32.8B | Q4_K_M | ≈22 GBFits in memory | ~9.6 tok/s |
Other GPUs that run Darwin-27B-RSI
Frequently asked questions
- Can the Tesla P40 run Darwin-27B-RSI?
- Yes. The Tesla P40 runs Darwin-27B-RSI fully in VRAM at Q5_K_M (about 23 GB of 24 GB), at roughly 10 tokens/s.
- How fast does Darwin-27B-RSI run on the Tesla P40?
- An estimate from memory bandwidth gives about 10 tokens/s at Q5_K_M.
- Which quantisation of Darwin-27B-RSI should I use on the Tesla P40?
- Q5_K_M: the largest one that fits. Expected quality: near-lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.