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 Radeon RX 9070 XT run plamo-3-translate-0.8b?

plamo-3-translate-0.8b·890M·Radeon RX 9070 XT·16 GB VRAM

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

Yes. The Radeon RX 9070 XT 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 Radeon RX 9070 XT

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 (640 GB/s); prompt processing and long contexts are slower.

Run plamo-3-translate-0.8b on the Radeon RX 9070 XT

Using FP16 / BF16, the best fit for Radeon RX 9070 XT.

Ollama · F16 straight from Hugging Facedocs
ollama run hf.co/mradermacher/plamo-3-translate-0.8b-GGUF:F16
Ollama · Docker with ROCm (AMD)docs
docker run -d --name ollama --device /dev/kfd --device /dev/dri \
  -v ollama:/root/.ollama -p 11434:11434 ollama/ollama:rocm
docker exec -it ollama ollama run hf.co/mradermacher/plamo-3-translate-0.8b-GGUF:F16

The image bundles the ROCm runtime; the host only needs the amdgpu kernel driver.

llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf mradermacher/plamo-3-translate-0.8b-GGUF:F16

Needs a HIP (ROCm) build of llama.cpp. Downloads the GGUF on first run.

llama.cpp · Docker with ROCm (AMD)docs
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
  -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
  ghcr.io/ggml-org/llama.cpp:server-rocm \
  -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`.

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve pfnet/plamo-3-translate-0.8b

Needs vLLM built for ROCm; it supports Instinct MI200/MI300 and Radeon RX 7900 / 9000 cards.

vLLM · Smaller FP8 builddocs
vllm serve pfnet/plamo-3-translate-0.8b-FP8
vLLM · Docker Compose (AMD ROCm)docs
services:
  vllm:
    image: rocm/vllm:latest
    command: vllm serve pfnet/plamo-3-translate-0.8b --host 0.0.0.0 --port 8000
    ports:
      - "8000:8000"
    ipc: host
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
    security_opt:
      - seccomp=unconfined
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface

AMD’s rocm/vllm image. API on port 8000.

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 Radeon RX 9070 XT 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 Radeon RX 9070 XT run plamo-3-translate-0.8b?
Yes. The Radeon RX 9070 XT 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 Radeon RX 9070 XT?
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.