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 Radeon RX 7800 XT run Bielik-11B-v3.1-Instruct?

Bielik-11B-v3.1-Instruct·11.2B·Radeon RX 7800 XT·16 GB VRAM

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

Yes. The Radeon RX 7800 XT runs Bielik-11B-v3.1-Instruct fully in VRAM at Q8_0 (about 13 GB of 16 GB), at roughly 29 tokens/s.

best quant
Q8_0
needs
13 GB
usable
16 GB
est. speed
~29 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 Radeon RX 7800 XT

QuantQualityMemoryFitSpeed
Q2_K Heavy loss5.3 GBfits~93 tok/s
Q3_K_M Noticeable loss7.0 GBfits~63 tok/s
Q4_K_M Small loss8.3 GBfits~51 tok/s
Q5_K_M Near-lossless9.4 GBfits~43 tok/s
Q6_K Near-lossless11 GBfits~37 tok/s
Q8_0 pickLossless13 GBfits~29 tok/s
FP16 / BF16 Lossless24 GBoffload~3.8 tok/s

Speed is a bandwidth-based estimate for generating text (624 GB/s); prompt processing and long contexts are slower.

Measured speed on the Radeon RX 7800 XT

No community reports for this pair yet.

Report your own speed →

Run Bielik-11B-v3.1-Instruct on the Radeon RX 7800 XT

Using Q8_0, the best fit for Radeon RX 7800 XT.

Ollama · Q8_0 straight from Hugging Facedocs
ollama run hf.co/speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q8_0
Ollama · Docker with ROCm (AMD)docs
docker run -d --name ollama --device /dev/kfd --device /dev/dri \
  -v ollama:/root/.ollama -p 11434:11434 ollama/ollama:rocm
docker exec -it ollama ollama run hf.co/speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q8_0

The image bundles the ROCm runtime; the host only needs the amdgpu kernel driver.

llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q8_0

Needs a HIP (ROCm) build of llama.cpp. Downloads the GGUF on first run.

llama.cpp · Docker with ROCm (AMD)docs
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-rocm \
  -hf speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99

Server and web UI on port 8080.

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. Needs vLLM built for ROCm; it supports Instinct MI200/MI300 and Radeon RX 7900 / 9000 cards.

vLLM · Smaller AWQ builddocs
vllm serve speakleash/Bielik-11B-v3.1-Instruct-AWQ
vLLM · Docker Compose (AMD ROCm)docs
services:
  vllm:
    image: rocm/vllm:latest
    command: vllm serve speakleash/Bielik-11B-v3.1-Instruct --host 0.0.0.0 --port 8000
    ports:
      - "8000:8000"
    ipc: host
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
    security_opt:
      - seccomp=unconfined
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    environment:
      - HF_TOKEN=${HF_TOKEN}

AMD’s rocm/vllm image. 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. Needs SGLang’s ROCm build (Instinct MI300-class GPUs).

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 Radeon RX 7800 XT comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8.2BQ8_0≈10 GBFits in memory~39 tok/sCommercial OK
14.8BQ6_K≈14 GBFits in memory~28 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~40 tok/sConditions
9.4BQ8_0≈11 GBFits in memory~34 tok/sCommercial OK
9.2BQ8_0≈13 GBFits in memory~35 tok/sConditions
ornith-ai logoOrnith-1.5-9Bornith-ai
9.7BQ8_0≈11 GBFits in memory~33 tok/sCommercial OK

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

Frequently asked questions

Can the Radeon RX 7800 XT run Bielik-11B-v3.1-Instruct?
Yes. The Radeon RX 7800 XT runs Bielik-11B-v3.1-Instruct fully in VRAM at Q8_0 (about 13 GB of 16 GB), at roughly 29 tokens/s.
How fast does Bielik-11B-v3.1-Instruct run on the Radeon RX 7800 XT?
An estimate from memory bandwidth gives about 29 tokens/s at Q8_0.
Which quantisation of Bielik-11B-v3.1-Instruct should I use on the Radeon RX 7800 XT?
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.