Yes. The Tesla P40 runs d1-2B fully in VRAM at FP16 / BF16 (about 4.3 GB of 24 GB), at roughly 50 tokens/s.
- best quant
- FP16 / BF16
- needs
- 4.3 GB
- usable
- 24 GB
- est. speed
- ~50 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the d1-2B page →
Every quantisation of d1-2B on the Tesla P40
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 1.5 GB | fits | ~303 tok/s |
| Q3_K_M | 1.8 GB | fits | ~204 tok/s |
| Q4_K_M | 1.9 GB | fits | ~164 tok/s |
| Q5_K_M | 2.1 GB | fits | ~140 tok/s |
| Q6_K | 2.4 GB | fits | ~121 tok/s |
| Q8_0 | 2.7 GB | fits | ~94 tok/s |
| FP16 / BF16 pick | 4.3 GB | fits | ~50 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 d1-2B on the Tesla P40
Using FP16 / BF16, the best fit for Tesla P40.
ollama run d1:2bThe library build picks its own default quantisation.
ollama run hf.co/LiquidAI/d1-2B-GGUF:F16 llama-server -hf LiquidAI/d1-2B-GGUF:F16Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get LiquidAI/d1-2B-GGUF@F16Then load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="LiquidAI/d1-2B", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Vision models that fit the Tesla P40 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 1.9B | Q8_0 | ≈2.7 GBFits in memory | ~94 tok/s | |
| 2.3B | Q8_0 | ≈2.8 GBFits in memory | ~79 tok/s | |
| 2.1B | Q8_0 | ≈3.2 GBFits in memory | ~84 tok/s | |
| 1.3B | Q8_0 | ≈1.7 GBFits in memory | ~138 tok/s | |
| 1.6B | Q8_0 | ≈1.9 GBFits in memory | ~116 tok/s | |
| 4.3B | Q8_0 | ≈5.2 GBFits in memory | ~42 tok/s |
Other GPUs that run d1-2B
Frequently asked questions
- Can the Tesla P40 run d1-2B?
- Yes. The Tesla P40 runs d1-2B fully in VRAM at FP16 / BF16 (about 4.3 GB of 24 GB), at roughly 50 tokens/s.
- How fast does d1-2B run on the Tesla P40?
- An estimate from memory bandwidth gives about 50 tokens/s at FP16 / BF16.
- Which quantisation of d1-2B 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.