selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

sensenova logo

Can the Tesla P40 run SenseNova-Loop-9B?

SenseNova-Loop-9B·9.4B·Tesla P40·24 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The Tesla P40 runs SenseNova-Loop-9B fully in VRAM at FP16 / BF16 (about 20 GB of 24 GB), at roughly 10 tokens/s.

best quant
FP16 / BF16
needs
20 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 SenseNova-Loop-9B page →

Every quantisation of SenseNova-Loop-9B on the Tesla P40

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.6 GBfits~62 tok/s
Q3_K_M Noticeable loss6.2 GBfits~41 tok/s
Q4_K_M Small loss7.1 GBfits~33 tok/s
Q5_K_M Near-lossless8.2 GBfits~29 tok/s
Q6_K Near-lossless9.2 GBfits~25 tok/s
Q8_0 Lossless11 GBfits~19 tok/s
FP16 / BF16 pickLossless20 GBfits~10 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 SenseNova-Loop-9B on the Tesla P40

Transformers · Ask about an imagedocs
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="sensenova/SenseNova-Loop-9B", 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"])

Gated on Hugging Face: accept the licence on the model page and export HF_TOKEN first.

Vision models that fit the Tesla P40 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
9.7BQ8_0≈11 GBFits in memory~19 tok/sCommercial OK
8.8BQ8_0≈10 GBFits in memory~20 tok/sCommercial OK
8.3BQ8_0≈8.9 GBFits in memory~22 tok/sCommercial OK
9.4BQ8_0≈11 GBFits in memory~19 tok/sCommercial OK
12.2BQ8_0≈16 GBFits in memory~15 tok/sConditions
Cloudflare logoclef-flashCloudflare
9.4BQ8_0≈11 GBFits in memory~19 tok/sCommercial OK

Other GPUs that run SenseNova-Loop-9B

Frequently asked questions

Can the Tesla P40 run SenseNova-Loop-9B?
Yes. The Tesla P40 runs SenseNova-Loop-9B fully in VRAM at FP16 / BF16 (about 20 GB of 24 GB), at roughly 10 tokens/s.
How fast does SenseNova-Loop-9B run on the Tesla P40?
An estimate from memory bandwidth gives about 10 tokens/s at FP16 / BF16.
Which quantisation of SenseNova-Loop-9B 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.