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.

pfnet logo

Can the Arc A580 run plamo-3-8b-fin-instruct?

plamo-3-8b-fin-instruct·8.5B·Arc A580·8 GB VRAM

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

Yes. The Arc A580 runs plamo-3-8b-fin-instruct fully in VRAM at Q5_K_M (about 7.0 GB of 8.0 GB), at roughly 46 tokens/s.

best quant
Q5_K_M
needs
7.0 GB
usable
8.0 GB
est. speed
~46 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the plamo-3-8b-fin-instruct page →

Every quantisation of plamo-3-8b-fin-instruct on the Arc A580

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.4 GBfits~100 tok/s
Q3_K_M Noticeable loss5.2 GBfits~68 tok/s
Q4_K_M Small loss6.2 GBfits~54 tok/s
Q5_K_M pickNear-lossless7.0 GBfits~46 tok/s
Q6_K Near-lossless7.8 GBtight~40 tok/s
Q8_0 Lossless9.9 GBoffload~13 tok/s
FP16 / BF16 Lossless18 GBoffload~3.2 tok/s

Speed is a bandwidth-based estimate for generating text (512 GB/s); prompt processing and long contexts are slower.

Measured speed on the Arc A580

No community reports for this pair yet.

Report your own speed →

Run plamo-3-8b-fin-instruct on the Arc A580

Using Q5_K_M, the best fit for Arc A580.

Ollama · Q5_K_M straight from Hugging Facedocs
ollama run hf.co/mradermacher/plamo-3-8b-fin-instruct-GGUF:Q5_K_M

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 mradermacher/plamo-3-8b-fin-instruct-GGUF:Q5_K_M

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 mradermacher/plamo-3-8b-fin-instruct-GGUF:Q5_K_M --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 mradermacher/plamo-3-8b-fin-instruct-GGUF@Q5_K_M

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="pfnet/plamo-3-8b-fin-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"])

Chat models that fit the Arc A580 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8.2BQ5_K_M≈7.3 GBFits in memory~48 tok/sCommercial OK
8BQ5_K_M≈7.1 GBFits in memory~49 tok/sConditions
8BQ5_K_M≈7.1 GBFits in memory~49 tok/sConditions
7.6BQ6_K≈7.0 GBFits in memory~45 tok/sCommercial OK
9.4BQ4_K_M≈7.2 GBFits in memory~49 tok/sCommercial OK
ibm-granite logogranite-4.2-8bibm-granite
8.8BQ4_K_M≈7.0 GBFits in memory~53 tok/sCommercial OK

Other GPUs that run plamo-3-8b-fin-instruct

Frequently asked questions

Can the Arc A580 run plamo-3-8b-fin-instruct?
Yes. The Arc A580 runs plamo-3-8b-fin-instruct fully in VRAM at Q5_K_M (about 7.0 GB of 8.0 GB), at roughly 46 tokens/s.
How fast does plamo-3-8b-fin-instruct run on the Arc A580?
An estimate from memory bandwidth gives about 46 tokens/s at Q5_K_M.
Which quantisation of plamo-3-8b-fin-instruct should I use on the Arc A580?
Q5_K_M: 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.