Can the Radeon RX 6700 XT run Bielik-11B-v3.1-Instruct?
Bielik-11B-v3.1-Instruct·11.2B·Radeon RX 6700 XT·12 GB VRAM
Yes. The Radeon RX 6700 XT runs Bielik-11B-v3.1-Instruct fully in VRAM at Q6_K (about 11 GB of 12 GB), at roughly 23 tokens/s.
- best quant
- Q6_K
- needs
- 11 GB
- usable
- 12 GB
- est. speed
- ~23 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 6700 XT
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 5.3 GB | fits | ~58 tok/s |
| Q3_K_M | 7.0 GB | fits | ~39 tok/s |
| Q4_K_M | 8.3 GB | fits | ~31 tok/s |
| Q5_K_M | 9.4 GB | fits | ~27 tok/s |
| Q6_K pick | 11 GB | fits | ~23 tok/s |
| Q8_0 | 13 GB | offload | ~12 tok/s |
| FP16 / BF16 | 24 GB | offload | ~2.6 tok/s |
Speed is a bandwidth-based estimate for generating text (384 GB/s); prompt processing and long contexts are slower.
Measured speed on the Radeon RX 6700 XT
No community reports for this pair yet.
Report your own speed →Run Bielik-11B-v3.1-Instruct on the Radeon RX 6700 XT
Using Q6_K, the best fit for Radeon RX 6700 XT.
ollama run hf.co/speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q6_Kdocker run -d --name ollama --device /dev/kfd --device /dev/dri \
-e HSA_OVERRIDE_GFX_VERSION=10.3.0 \
-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:Q6_KROCm doesn’t ship kernels for this card; -e HSA_OVERRIDE_GFX_VERSION=10.3.0 makes it run as the nearest supported target.
llama-server -hf speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q6_KNeeds a HIP (ROCm) build of llama.cpp. Start it with HSA_OVERRIDE_GFX_VERSION=10.3.0 in front for this card. Downloads the GGUF on first run.
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
-e HSA_OVERRIDE_GFX_VERSION=10.3.0 \
-v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
ghcr.io/ggml-org/llama.cpp:server-rocm \
-hf speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q6_K --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get speakleash/Bielik-11B-v3.1-Instruct-GGUF@Q6_KThen 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 6700 XT comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 8.2B | Q8_0 | ≈10 GBFits in memory | ~24 tok/s | |
| 14.8B | Q4_K_M | ≈11 GBFits in memory | ~24 tok/s | |
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~25 tok/s | |
| 9.4B | Q8_0 | ≈11 GBFits in memory | ~21 tok/s | |
| 9.2B | Q6_K | ≈11 GBFits in memory | ~28 tok/s | |
| 9.7B | Q8_0 | ≈11 GBFits in memory | ~21 tok/s |
Other GPUs that run Bielik-11B-v3.1-Instruct
Frequently asked questions
- Can the Radeon RX 6700 XT run Bielik-11B-v3.1-Instruct?
- Yes. The Radeon RX 6700 XT runs Bielik-11B-v3.1-Instruct fully in VRAM at Q6_K (about 11 GB of 12 GB), at roughly 23 tokens/s.
- How fast does Bielik-11B-v3.1-Instruct run on the Radeon RX 6700 XT?
- An estimate from memory bandwidth gives about 23 tokens/s at Q6_K.
- Which quantisation of Bielik-11B-v3.1-Instruct should I use on the Radeon RX 6700 XT?
- 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.