Can the Tesla P40 run Spark-X2.6-1.7B?
Spark-X2.6-1.7B·1.7B·Tesla P40·24 GB VRAM
Yes. The Tesla P40 runs Spark-X2.6-1.7B fully in VRAM at FP16 / BF16 (about 4.3 GB of 24 GB), at roughly 56 tokens/s.
- best quant
- FP16 / BF16
- needs
- 4.3 GB
- usable
- 24 GB
- est. speed
- ~56 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Spark-X2.6-1.7B page →
Every quantisation of Spark-X2.6-1.7B on the Tesla P40
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 1.5 GB | fits | ~340 tok/s |
| Q3_K_M | 1.8 GB | fits | ~229 tok/s |
| Q4_K_M | 2.7 GB | fits | ~184 tok/s |
| Q5_K_M | 2.1 GB | fits | ~157 tok/s |
| Q6_K | 2.3 GB | fits | ~136 tok/s |
| Q8_0 | 2.7 GB | fits | ~105 tok/s |
| FP16 / BF16 pick | 4.3 GB | fits | ~56 tok/s |
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 Spark-X2.6-1.7B on the Tesla P40
Using Q8_0, the best fit for Tesla P40.
ollama run hf.co/XHToken/Spark-X2.6-1.7B-GGUF:Q8_0 llama-server -hf XHToken/Spark-X2.6-1.7B-GGUF:Q8_0Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get XHToken/Spark-X2.6-1.7B-GGUF@Q8_0Then load it from the LM Studio app or with `lms load`.
sglang serve XHToken/Spark-X2.6-1.7B --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve XHToken/Spark-X2.6-1.7B --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="XHToken/Spark-X2.6-1.7B", 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 |
|---|---|---|---|---|
| 1.7B | Q8_0 | ≈2.7 GBFits in memory | ~104 tok/s | |
| 1.5B | Q8_0 | ≈2.6 GBFits in memory | ~116 tok/s | |
| 2B | Q8_0 | ≈3.2 GBFits in memory | ~88 tok/s | |
| 1.2B | Q8_0 | ≈2.0 GBFits in memory | ~145 tok/s | |
| 1B | Q8_0 | ≈1.8 GBFits in memory | ~180 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~56 tok/s |
Other GPUs that run Spark-X2.6-1.7B
Frequently asked questions
- Can the Tesla P40 run Spark-X2.6-1.7B?
- Yes. The Tesla P40 runs Spark-X2.6-1.7B fully in VRAM at FP16 / BF16 (about 4.3 GB of 24 GB), at roughly 56 tokens/s.
- How fast does Spark-X2.6-1.7B run on the Tesla P40?
- An estimate from memory bandwidth gives about 56 tokens/s at FP16 / BF16.
- Which quantisation of Spark-X2.6-1.7B should I use on the Tesla P40?
- FP16 / BF16: the largest one that fits. Expected quality: 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.