Can the Radeon RX 7900 XTX run plamo-3-translate-31b?
plamo-3-translate-31b·31.8B·Radeon RX 7900 XTX·24 GB VRAM
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
| Quant | Memory | Fit |
|---|---|---|
| Q4_K_M pick | 22 GB | fits |
| Q8_0 | 38 GB | too big |
| FP16 / BF16 | 71 GB | too 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 run hf.co/pfnet/plamo-3-translate-31b-GGUF:Q4_K_Mdocker 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_MThe image bundles the ROCm runtime; the host only needs the amdgpu kernel driver.
llama-server -hf pfnet/plamo-3-translate-31b-GGUF:Q4_K_MNeeds a HIP (ROCm) build of llama.cpp. Downloads the GGUF on first run.
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 99Server and web UI on port 8080.
lms get pfnet/plamo-3-translate-31b-GGUF@Q4_K_MThen load it from the LM Studio app or with `lms load`.
vllm serve pfnet/plamo-3-translate-31bNeeds vLLM built for ROCm; it supports Instinct MI200/MI300 and Radeon RX 7900 / 9000 cards.
vllm serve pfnet/plamo-3-translate-31b-FP8services:
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/huggingfaceAMD’s rocm/vllm image. API on port 8000.
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 →| Model | Params | Best quant | Memory |
|---|---|---|---|
| 9.7B | FP16 / BF16 | ≈22 GBFits in memory | |
| 8B | FP16 / BF16 | ≈18 GBFits in memory | |
| 10.2B | Q8_0 | ≈13 GBFits in memory | |
| 8B | FP16 / BF16 | ≈18 GBFits in memory | |
| 8.5B | FP16 / BF16 | ≈20 GBFits in memory | |
| 9.5B | FP16 / BF16 | ≈22 GBFits in memory |
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.