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.

pfnet logo

Can the Tesla P40 run plamo-3-translate-8b?

plamo-3-translate-8b·8.5B·Tesla P40·24 GB VRAM

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

Yes. The Tesla P40 runs plamo-3-translate-8b fully in VRAM at FP16 / BF16 (about 20 GB of 24 GB).

best quant
FP16 / BF16
needs
20 GB
usable
24 GB

Estimates from the model's size.Try other contexts on the plamo-3-translate-8b page →

Every quantisation of plamo-3-translate-8b on the Tesla P40

QuantMemoryFit
Q4_K_M 6.4 GBfits
Q8_0 11 GBfits
FP16 / BF16 pick20 GBfits

Speed is a bandwidth-based estimate for generating text (347 GB/s); prompt processing and long contexts are slower.

Run plamo-3-translate-8b on the Tesla P40

Using Q6_K, the best fit for Tesla P40.

Ollama · Q6_K straight from Hugging Facedocs
ollama run hf.co/mradermacher/plamo-3-translate-8b-i1-GGUF:Q6_K
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf mradermacher/plamo-3-translate-8b-i1-GGUF:Q6_K

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

LM Studio · Download with the lms CLIdocs
lms get mradermacher/plamo-3-translate-8b-i1-GGUF@Q6_K

Then load it from the LM Studio app or with `lms load`.

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve pfnet/plamo-3-translate-8b
vLLM · Smaller FP8 builddocs
vllm serve pfnet/plamo-3-translate-8b-FP8
vLLM · Docker Compose (NVIDIA)docs
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: pfnet/plamo-3-translate-8b
    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.

Transformers · Run with the translation pipelinedocs
from transformers import pipeline

pipe = pipeline("translation", model="pfnet/plamo-3-translate-8b")
result = pipe("Self-hosting puts you in control of your data.")
print(result)

Translation models that fit the Tesla P40 comfortably

All that fit →
ModelParamsBest quantMemoryLicence
tencent logoHy-MT2-7Btencent
8BFP16 / BF16≈18 GBFits in memoryCommercial OK
8BFP16 / BF16≈18 GBFits in memoryCheck licence
9.7BFP16 / BF16≈22 GBFits in memoryCommercial OK
ByteDance-Seed logoSeed-X-PPO-7BByteDance-Seed
7.5BFP16 / BF16≈17 GBFits in memoryCommercial OK
8BFP16 / BF16≈18 GBFits in memoryCheck licence
ByteDance-Seed logoSeed-X-Instruct-7BByteDance-Seed
7.5BFP16 / BF16≈17 GBFits in memoryCommercial OK

Other GPUs that run plamo-3-translate-8b

Frequently asked questions

Can the Tesla P40 run plamo-3-translate-8b?
Yes. The Tesla P40 runs plamo-3-translate-8b fully in VRAM at FP16 / BF16 (about 20 GB of 24 GB).
Which quantisation of plamo-3-translate-8b 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.