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.

speakleash logo

Can the Tesla P40 run Bielik-11B-v3.1-Instruct?

Bielik-11B-v3.1-Instruct·11.2B·Tesla P40·24 GB VRAM

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

Yes. The Tesla P40 runs Bielik-11B-v3.1-Instruct fully in VRAM at Q8_0 (about 13 GB of 24 GB), at roughly 16 tokens/s.

best quant
Q8_0
needs
13 GB
usable
24 GB
est. speed
~16 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Bielik-11B-v3.1-Instruct page →

Every quantisation of Bielik-11B-v3.1-Instruct on the Tesla P40

QuantQualityMemoryFitSpeed
Q2_K Heavy loss5.3 GBfits~52 tok/s
Q3_K_M Noticeable loss7.0 GBfits~35 tok/s
Q4_K_M Small loss8.3 GBfits~28 tok/s
Q5_K_M Near-lossless9.4 GBfits~24 tok/s
Q6_K Near-lossless11 GBfits~21 tok/s
Q8_0 pickLossless13 GBfits~16 tok/s
FP16 / BF16 Lossless24 GBtight~8.5 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 Bielik-11B-v3.1-Instruct on the Tesla P40

Using Q8_0, the best fit for Tesla P40.

Ollama · Q8_0 straight from Hugging Facedocs
ollama run hf.co/speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q8_0
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q8_0

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 speakleash/Bielik-11B-v3.1-Instruct-GGUF@Q8_0

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

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve speakleash/Bielik-11B-v3.1-Instruct

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

vLLM · Smaller AWQ builddocs
vllm serve speakleash/Bielik-11B-v3.1-Instruct-AWQ
vLLM · Docker Compose (NVIDIA)docs
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: speakleash/Bielik-11B-v3.1-Instruct
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    environment:
      - HF_TOKEN=${HF_TOKEN}
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 8000.

SGLang · Serve an OpenAI-compatible APIdocs
sglang serve speakleash/Bielik-11B-v3.1-Instruct --host 0.0.0.0 --port 30000

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

SGLang · Docker Compose (NVIDIA)docs
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve speakleash/Bielik-11B-v3.1-Instruct --host 0.0.0.0 --port 30000
    ports:
      - "30000:30000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    environment:
      - HF_TOKEN=${HF_TOKEN}
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 30000.

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="speakleash/Bielik-11B-v3.1-Instruct", 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"])

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

Chat models that fit the Tesla P40 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8.2BQ8_0≈10 GBFits in memory~22 tok/sCommercial OK
14.8BQ8_0≈17 GBFits in memory~12 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
7.6BQ8_0≈8.9 GBFits in memory~24 tok/sCommercial OK

Other GPUs that run Bielik-11B-v3.1-Instruct

Frequently asked questions

Can the Tesla P40 run Bielik-11B-v3.1-Instruct?
Yes. The Tesla P40 runs Bielik-11B-v3.1-Instruct fully in VRAM at Q8_0 (about 13 GB of 24 GB), at roughly 16 tokens/s.
How fast does Bielik-11B-v3.1-Instruct run on the Tesla P40?
An estimate from memory bandwidth gives about 16 tokens/s at Q8_0.
Which quantisation of Bielik-11B-v3.1-Instruct should I use on the Tesla P40?
Q8_0: 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.