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 Arc B580 run Bielik-11B-v3.1-Instruct?

Bielik-11B-v3.1-Instruct·11.2B·Arc B580·12 GB VRAM

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

Yes. The Arc B580 runs Bielik-11B-v3.1-Instruct fully in VRAM at Q6_K (about 11 GB of 12 GB), at roughly 27 tokens/s.

best quant
Q6_K
needs
11 GB
usable
12 GB
est. speed
~27 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 Arc B580

QuantQualityMemoryFitSpeed
Q2_K Heavy loss5.3 GBfits~68 tok/s
Q3_K_M Noticeable loss7.0 GBfits~46 tok/s
Q4_K_M Small loss8.3 GBfits~37 tok/s
Q5_K_M Near-lossless9.4 GBfits~32 tok/s
Q6_K pickNear-lossless11 GBfits~27 tok/s
Q8_0 Lossless13 GBoffload~13 tok/s
FP16 / BF16 Lossless24 GBoffload~2.6 tok/s

Speed is a bandwidth-based estimate for generating text (456 GB/s); prompt processing and long contexts are slower.

Measured speed on the Arc B580

No community reports for this pair yet.

Report your own speed →

Run Bielik-11B-v3.1-Instruct on the Arc B580

Using Q6_K, the best fit for Arc B580.

Ollama · Q6_K straight from Hugging Facedocs
ollama run hf.co/speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q6_K

Ollama’s ROCm/CUDA builds don’t cover this GPU. Recent Ollama releases use Vulkan when its Vulkan backend and driver are installed (older ones needed OLLAMA_VULKAN=1); llama.cpp or LM Studio with Vulkan are the safer bet.

llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q6_K

Needs a Vulkan build of llama.cpp. Downloads the GGUF on first run.

llama.cpp · Docker with Vulkandocs
docker run -d --name llama --device /dev/dri -p 8080:8080 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-vulkan \
  -hf speakleash/Bielik-11B-v3.1-Instruct-GGUF:Q6_K --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@Q6_K

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

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 Arc B580 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8.2BQ8_0≈10 GBFits in memory~29 tok/sCommercial OK
14.8BQ4_K_M≈11 GBFits in memory~28 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~29 tok/sConditions
9.4BQ8_0≈11 GBFits in memory~25 tok/sCommercial OK
9.2BQ6_K≈11 GBFits in memory~33 tok/sConditions
ornith-ai logoOrnith-1.5-9Bornith-ai
9.7BQ8_0≈11 GBFits in memory~24 tok/sCommercial OK

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

Frequently asked questions

Can the Arc B580 run Bielik-11B-v3.1-Instruct?
Yes. The Arc B580 runs Bielik-11B-v3.1-Instruct fully in VRAM at Q6_K (about 11 GB of 12 GB), at roughly 27 tokens/s.
How fast does Bielik-11B-v3.1-Instruct run on the Arc B580?
An estimate from memory bandwidth gives about 27 tokens/s at Q6_K.
Which quantisation of Bielik-11B-v3.1-Instruct should I use on the Arc B580?
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.