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 RTX 4070 run Bielik-11B-v3.1-Instruct?

Bielik-11B-v3.1-Instruct·11.2B·GeForce RTX 4070·12 GB VRAM

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

Yes. The RTX 4070 runs Bielik-11B-v3.1-Instruct fully in VRAM at Q6_K (about 11 GB of 12 GB), at roughly 30 tokens/s.

best quant
Q6_K
needs
11 GB
usable
12 GB
est. speed
~30 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 RTX 4070

QuantQualityMemoryFitSpeed
Q2_K Heavy loss5.3 GBfits~75 tok/s
Q3_K_M Noticeable loss7.0 GBfits~51 tok/s
Q4_K_M Small loss8.3 GBfits~41 tok/s
Q5_K_M Near-lossless9.4 GBfits~35 tok/s
Q6_K pickNear-lossless11 GBfits~30 tok/s
Q8_0 Lossless13 GBoffload~14 tok/s
FP16 / BF16 Lossless24 GBoffload~2.7 tok/s

Speed is a bandwidth-based estimate for generating text (504 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX 4070

No community reports for this pair yet.

Report your own speed →

Run Bielik-11B-v3.1-Instruct on the RTX 4070

Using Q6_K, the best fit for RTX 4070.

Ollama · Q6_K straight from Hugging Facedocs
ollama run hf.co/speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q6_K
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf speakleash/Bielik-11B-v3.1-Instruct-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 speakleash/Bielik-11B-v3.1-Instruct-GGUF@Q6_K

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 RTX 4070 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8.2BQ8_0≈10 GBFits in memory~32 tok/sCommercial OK
14.8BQ4_K_M≈11 GBFits in memory~31 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~32 tok/sConditions
9.4BQ8_0≈11 GBFits in memory~28 tok/sCommercial OK
9.2BQ6_K≈11 GBFits in memory~36 tok/sConditions
ornith-ai logoOrnith-1.5-9Bornith-ai
9.7BQ8_0≈11 GBFits in memory~27 tok/sCommercial OK

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

Frequently asked questions

Can the RTX 4070 run Bielik-11B-v3.1-Instruct?
Yes. The RTX 4070 runs Bielik-11B-v3.1-Instruct fully in VRAM at Q6_K (about 11 GB of 12 GB), at roughly 30 tokens/s.
How fast does Bielik-11B-v3.1-Instruct run on the RTX 4070?
An estimate from memory bandwidth gives about 30 tokens/s at Q6_K.
Which quantisation of Bielik-11B-v3.1-Instruct should I use on the RTX 4070?
Q6_K: the largest one that fits. Expected quality: near-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.