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 7900 XTX run plamo-3-translate-31b?

plamo-3-translate-31b·31.8B·Radeon RX 7900 XTX·24 GB VRAM

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

Yes. The Radeon RX 7900 XTX runs plamo-3-translate-31b fully in VRAM at Q4_K_M (about 22 GB of 24 GB).

best quant
Q4_K_M
needs
22 GB
usable
24 GB

Estimates from the model's size.Try other contexts on the plamo-3-translate-31b page →

Every quantisation of plamo-3-translate-31b on the Radeon RX 7900 XTX

QuantMemoryFit
Q4_K_M pick22 GBfits
Q8_0 38 GBtoo big
FP16 / BF16 71 GBtoo big

Speed is a bandwidth-based estimate for generating text (960 GB/s); prompt processing and long contexts are slower.

Run plamo-3-translate-31b on the Radeon RX 7900 XTX

Using Q4_K_M, the best fit for Radeon RX 7900 XTX.

Ollama · Q4_K_M straight from Hugging Facedocs
ollama run hf.co/pfnet/plamo-3-translate-31b-GGUF:Q4_K_M
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/pfnet/plamo-3-translate-31b-GGUF:Q4_K_M

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 pfnet/plamo-3-translate-31b-GGUF:Q4_K_M

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 pfnet/plamo-3-translate-31b-GGUF:Q4_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 pfnet/plamo-3-translate-31b-GGUF@Q4_K_M

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

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve pfnet/plamo-3-translate-31b

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-31b-FP8
vLLM · Docker Compose (AMD ROCm)docs
services:
  vllm:
    image: rocm/vllm:latest
    command: vllm serve pfnet/plamo-3-translate-31b --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-31b")
result = pipe("Self-hosting puts you in control of your data.")
print(result)

Translation models that fit the Radeon RX 7900 XTX comfortably

All that fit →
ModelParamsBest quantMemoryLicence
9.7BFP16 / BF16≈22 GBFits in memoryCommercial OK
tencent logoHy-MT2-7Btencent
8BFP16 / BF16≈18 GBFits in memoryCommercial OK
10.2BQ8_0≈13 GBFits in memoryConditions
8BFP16 / BF16≈18 GBFits in memoryCheck licence
8.5BFP16 / BF16≈20 GBFits in memoryConditions
9.5BFP16 / BF16≈22 GBFits in memoryConditions

Other GPUs that run plamo-3-translate-31b

Frequently asked questions

Can the Radeon RX 7900 XTX run plamo-3-translate-31b?
Yes. The Radeon RX 7900 XTX runs plamo-3-translate-31b fully in VRAM at Q4_K_M (about 22 GB of 24 GB).
Which quantisation of plamo-3-translate-31b should I use on the Radeon RX 7900 XTX?
Q4_K_M: the largest one that fits. Expected quality: small loss 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.