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
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
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 5.3 GB | fits | ~93 tok/s |
| Q3_K_M | 7.0 GB | fits | ~63 tok/s |
| Q4_K_M | 8.3 GB | fits | ~51 tok/s |
| Q5_K_M | 9.4 GB | fits | ~43 tok/s |
| Q6_K | 11 GB | fits | ~37 tok/s |
| Q8_0 pick | 13 GB | fits | ~29 tok/s |
| FP16 / BF16 | 24 GB | offload | ~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 run hf.co/speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q8_0docker 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_0The image bundles the ROCm runtime; the host only needs the amdgpu kernel driver.
llama-server -hf speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q8_0Needs a HIP (ROCm) build of llama.cpp. Downloads the GGUF on first run.
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 99Server and web UI on port 8080.
lms get speakleash/Bielik-11B-v3.1-Instruct-GGUF@Q8_0Then load it from the LM Studio app or with `lms load`.
vllm serve speakleash/Bielik-11B-v3.1-InstructGated 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 serve speakleash/Bielik-11B-v3.1-Instruct-AWQservices:
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 speakleash/Bielik-11B-v3.1-Instruct --host 0.0.0.0 --port 30000Gated on Hugging Face: accept the licence on the model page and export HF_TOKEN first. Needs SGLang’s ROCm build (Instinct MI300-class GPUs).
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 →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 8.2B | Q8_0 | ≈10 GBFits in memory | ~39 tok/s | |
| 14.8B | Q6_K | ≈14 GBFits in memory | ~28 tok/s | |
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~40 tok/s | |
| 9.4B | Q8_0 | ≈11 GBFits in memory | ~34 tok/s | |
| 9.2B | Q8_0 | ≈13 GBFits in memory | ~35 tok/s | |
| 9.7B | Q8_0 | ≈11 GBFits in memory | ~33 tok/s |
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.