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-translate-0.8b?

plamo-3-translate-0.8b·890M·Arc A770 16GB·16 GB VRAM

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

Yes. The Arc A770 16GB runs plamo-3-translate-0.8b fully in VRAM at FP16 / BF16 (about 2.5 GB of 16 GB).

best quant
FP16 / BF16
needs
2.5 GB
usable
16 GB

Estimates from the model's size.Try other contexts on the plamo-3-translate-0.8b page →

Every quantisation of plamo-3-translate-0.8b on the Arc A770 16GB

QuantMemoryFit
Q4_K_M 1.1 GBfits
Q8_0 1.6 GBfits
FP16 / BF16 pick2.5 GBfits

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

Run plamo-3-translate-0.8b on the Arc A770 16GB

Using FP16 / BF16, the best fit for Arc A770 16GB.

Ollama · F16 straight from Hugging Facedocs
ollama run hf.co/mradermacher/plamo-3-translate-0.8b-GGUF:F16

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-translate-0.8b-GGUF:F16

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-translate-0.8b-GGUF:F16 --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-translate-0.8b-GGUF@F16

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

Transformers · Run with the translation pipelinedocs
from transformers import pipeline

pipe = pipeline("translation", model="pfnet/plamo-3-translate-0.8b")
result = pipe("Self-hosting puts you in control of your data.")
print(result)

Translation models that fit the Arc A770 16GB comfortably

All that fit →
ModelParamsBest quantMemoryLicence
600MFP16 / BF16≈1.8 GBFits in memoryNon-commercial
1.1BFP16 / BF16≈3.0 GBFits in memoryCommercial OK
1.3BFP16 / BF16≈3.4 GBFits in memoryNon-commercial
2BFP16 / BF16≈5.1 GBFits in memoryCommercial OK
2BFP16 / BF16≈5.1 GBFits in memoryCheck licence
2.3BFP16 / BF16≈5.6 GBFits in memoryCommercial OK

Other GPUs that run plamo-3-translate-0.8b

Frequently asked questions

Can the Arc A770 16GB run plamo-3-translate-0.8b?
Yes. The Arc A770 16GB runs plamo-3-translate-0.8b fully in VRAM at FP16 / BF16 (about 2.5 GB of 16 GB).
Which quantisation of plamo-3-translate-0.8b should I use on the Arc A770 16GB?
FP16 / BF16: 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.