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 A770 16GB run plamo-3-8b-fin-instruct?

plamo-3-8b-fin-instruct·8.5B·Arc A770 16GB·16 GB VRAM

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

Yes. The Arc A770 16GB runs plamo-3-8b-fin-instruct fully in VRAM at Q8_0 (about 9.9 GB of 16 GB), at roughly 34 tokens/s.

best quant
Q8_0
needs
9.9 GB
usable
16 GB
est. speed
~34 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 A770 16GB

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.4 GBfits~110 tok/s
Q3_K_M Noticeable loss5.2 GBfits~74 tok/s
Q4_K_M Small loss6.2 GBfits~60 tok/s
Q5_K_M Near-lossless7.0 GBfits~51 tok/s
Q6_K Near-lossless7.8 GBfits~44 tok/s
Q8_0 pickLossless9.9 GBfits~34 tok/s
FP16 / BF16 Lossless18 GBoffload~10 tok/s

Speed is a bandwidth-based estimate for generating text (560 GB/s); prompt processing and long contexts are slower.

Measured speed on the Arc A770 16GB

No community reports for this pair yet.

Report your own speed →

Run plamo-3-8b-fin-instruct on the Arc A770 16GB

Using Q8_0, the best fit for Arc A770 16GB.

Ollama · Q8_0 straight from Hugging Facedocs
ollama run hf.co/mradermacher/plamo-3-8b-fin-instruct-GGUF:Q8_0

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:Q8_0

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: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 mradermacher/plamo-3-8b-fin-instruct-GGUF@Q8_0

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 A770 16GB comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8.2BQ8_0≈10 GBFits in memory~35 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~36 tok/sConditions
8BQ8_0≈9.8 GBFits in memory~36 tok/sConditions
7.6BQ8_0≈8.9 GBFits in memory~38 tok/sCommercial OK
9.4BQ8_0≈11 GBFits in memory~31 tok/sCommercial OK
9.2BQ8_0≈13 GBFits in memory~31 tok/sConditions

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

Frequently asked questions

Can the Arc A770 16GB run plamo-3-8b-fin-instruct?
Yes. The Arc A770 16GB runs plamo-3-8b-fin-instruct fully in VRAM at Q8_0 (about 9.9 GB of 16 GB), at roughly 34 tokens/s.
How fast does plamo-3-8b-fin-instruct run on the Arc A770 16GB?
An estimate from memory bandwidth gives about 34 tokens/s at Q8_0.
Which quantisation of plamo-3-8b-fin-instruct should I use on the Arc A770 16GB?
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.