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.

ByteDance-Seed logo

Can the Tesla P40 run Cola2?

Cola2·8.8B·Tesla P40·24 GB VRAM

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

Yes. The Tesla P40 runs Cola2 fully in VRAM at FP16 / BF16 (about 19 GB of 24 GB), at roughly 11 tokens/s.

best quant
FP16 / BF16
needs
19 GB
usable
24 GB
est. speed
~11 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Cola2 page →

Every quantisation of Cola2 on the Tesla P40

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.4 GBfits~66 tok/s
Q3_K_M Noticeable loss5.8 GBfits~45 tok/s
Q4_K_M Small loss6.8 GBfits~36 tok/s
Q5_K_M Near-lossless7.7 GBfits~31 tok/s
Q6_K Near-lossless8.6 GBfits~26 tok/s
Q8_0 Lossless11 GBfits~20 tok/s
FP16 / BF16 pickLossless19 GBfits~11 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 Cola2 on the Tesla P40

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="ByteDance-Seed/Cola2", 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 →
ModelParamsBest quantMemorySpeedLicence
8.2BQ8_0≈10 GBFits in memory~22 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~22 tok/sConditions
7.6BQ8_0≈8.9 GBFits in memory~24 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~22 tok/sConditions
9.4BQ8_0≈11 GBFits in memory~19 tok/sCommercial OK
9.2BQ8_0≈13 GBFits in memory~19 tok/sConditions

Other GPUs that run Cola2

Frequently asked questions

Can the Tesla P40 run Cola2?
Yes. The Tesla P40 runs Cola2 fully in VRAM at FP16 / BF16 (about 19 GB of 24 GB), at roughly 11 tokens/s.
How fast does Cola2 run on the Tesla P40?
An estimate from memory bandwidth gives about 11 tokens/s at FP16 / BF16.
Which quantisation of Cola2 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.