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-8b?

plamo-3-translate-8b·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-translate-8b fully in VRAM at Q8_0 (about 11 GB of 16 GB).

best quant
Q8_0
needs
11 GB
usable
16 GB

Estimates from the model's size.Try other contexts on the plamo-3-translate-8b page →

Every quantisation of plamo-3-translate-8b on the Arc A770 16GB

QuantMemoryFit
Q4_K_M 6.4 GBfits
Q8_0 pick11 GBfits
FP16 / BF16 20 GBtoo big

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

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

Using Q6_K, the best fit for Arc A770 16GB.

Ollama · Q6_K straight from Hugging Facedocs
ollama run hf.co/mradermacher/plamo-3-translate-8b-i1-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 mradermacher/plamo-3-translate-8b-i1-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 mradermacher/plamo-3-translate-8b-i1-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 mradermacher/plamo-3-translate-8b-i1-GGUF@Q6_K

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-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
tencent logoHy-MT2-7Btencent
8BQ8_0≈10 GBFits in memoryCommercial OK
8BQ8_0≈10 GBFits in memoryCheck licence
9.7BQ8_0≈12 GBFits in memoryCommercial OK
ByteDance-Seed logoSeed-X-PPO-7BByteDance-Seed
7.5BQ8_0≈9.4 GBFits in memoryCommercial OK
8BQ8_0≈10 GBFits in memoryCheck licence
ByteDance-Seed logoSeed-X-Instruct-7BByteDance-Seed
7.5BQ8_0≈9.4 GBFits in memoryCommercial OK

Other GPUs that run plamo-3-translate-8b

Frequently asked questions

Can the Arc A770 16GB run plamo-3-translate-8b?
Yes. The Arc A770 16GB runs plamo-3-translate-8b fully in VRAM at Q8_0 (about 11 GB of 16 GB).
Which quantisation of plamo-3-translate-8b 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.