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-3-8b-fin-instruct?

plamo-3-8b-fin-instruct·8.5B·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-3-8b-fin-instruct fully in VRAM at Q8_0 (about 9.9 GB of 16 GB), at roughly 39 tokens/s.

best quant
Q8_0
needs
9.9 GB
usable
16 GB
est. speed
~39 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the plamo-3-8b-fin-instruct page →

Every quantisation of plamo-3-8b-fin-instruct on the Radeon RX 9070 XT

QuantQualityMemoryFitSpeed
Q2_K Heavy loss3.7 GBfits~125 tok/s
Q3_K_M Noticeable loss5.1 GBfits~84 tok/s
Q4_K_M Small loss6.2 GBfits~68 tok/s
Q5_K_M Near-lossless6.9 GBfits~58 tok/s
Q6_K Near-lossless7.9 GBfits~50 tok/s
Q8_0 pickLossless9.9 GBfits~39 tok/s
FP16 / BF16 Lossless18 GBoffload~11 tok/s

Speed is a bandwidth-based estimate for generating text (640 GB/s); prompt processing and long contexts are slower.

Measured speed on the Radeon RX 9070 XT

No community reports for this pair yet.

Report your own speed →

Run plamo-3-8b-fin-instruct on the Radeon RX 9070 XT

Using Q8_0, the best fit for Radeon RX 9070 XT.

Ollama · Q8_0 straight from Hugging Facedocs
ollama run hf.co/rSalone/PLaMo-3-8B-Fin-Instruct-GGUF:Q8_0
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/rSalone/PLaMo-3-8B-Fin-Instruct-GGUF:Q8_0

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 rSalone/PLaMo-3-8B-Fin-Instruct-GGUF:Q8_0

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 rSalone/PLaMo-3-8B-Fin-Instruct-GGUF:Q8_0 --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 rSalone/PLaMo-3-8B-Fin-Instruct-GGUF@Q8_0

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

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve pfnet/plamo-3-8b-fin-instruct

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

vLLM · Docker Compose (AMD ROCm)docs
services:
  vllm:
    image: rocm/vllm:latest
    command: vllm serve pfnet/plamo-3-8b-fin-instruct --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 · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="pfnet/plamo-3-8b-fin-instruct", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])

Chat models that fit the Radeon RX 9070 XT comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8.2BQ8_0≈10 GBFits in memory~40 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~41 tok/sConditions
7.6BQ8_0≈8.9 GBFits in memory~44 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~41 tok/sConditions
9.2BQ8_0≈13 GBFits in memory~36 tok/sConditions
7.2BQ8_0≈9.0 GBFits in memory~46 tok/sCommercial OK

Other GPUs that run plamo-3-8b-fin-instruct

Frequently asked questions

Can the Radeon RX 9070 XT run plamo-3-8b-fin-instruct?
Yes. The Radeon RX 9070 XT runs plamo-3-8b-fin-instruct fully in VRAM at Q8_0 (about 9.9 GB of 16 GB), at roughly 39 tokens/s.
How fast does plamo-3-8b-fin-instruct run on the Radeon RX 9070 XT?
An estimate from memory bandwidth gives about 39 tokens/s at Q8_0.
Which quantisation of plamo-3-8b-fin-instruct should I use on the Radeon RX 9070 XT?
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.