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.

NousResearch logo

Can the Radeon RX 7900 XTX run Arete-27B?

Arete-27B·27.4B·Radeon RX 7900 XTX·24 GB VRAM

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

Yes. The Radeon RX 7900 XTX runs Arete-27B fully in VRAM at Q5_K_M (about 23 GB of 24 GB), at roughly 27 tokens/s.

best quant
Q5_K_M
needs
23 GB
usable
24 GB
est. speed
~27 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Arete-27B page →

Every quantisation of Arete-27B on the Radeon RX 7900 XTX

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~59 tok/s
Q3_K_M Noticeable loss15 GBfits~39 tok/s
Q4_K_M Small loss19 GBfits~32 tok/s
Q5_K_M pickNear-lossless23 GBfits~27 tok/s
Q6_K Near-lossless26 GBoffload~12 tok/s
Q8_0 Lossless31 GBoffload~4.3 tok/s
FP16 / BF16 Lossless55 GBtoo big—

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

Measured speed on the Radeon RX 7900 XTX

No community reports for this pair yet.

Report your own speed →

Run Arete-27B on the Radeon RX 7900 XTX

Using Q5_K_M, the best fit for Radeon RX 7900 XTX.

Ollama · Q5_K_M straight from Hugging Facedocs
ollama run hf.co/bartowski/NousResearch_Arete-27B-GGUF:Q5_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/bartowski/NousResearch_Arete-27B-GGUF:Q5_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 bartowski/NousResearch_Arete-27B-GGUF:Q5_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 bartowski/NousResearch_Arete-27B-GGUF:Q5_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 bartowski/NousResearch_Arete-27B-GGUF@Q5_K_M

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

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve NousResearch/Arete-27B

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

vLLM · Smaller FP8 builddocs
vllm serve processreap/Arete-27B-FP8
vLLM · Docker Compose (AMD ROCm)docs
services:
  vllm:
    image: rocm/vllm:latest
    command: vllm serve NousResearch/Arete-27B --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.

SGLang · Serve an OpenAI-compatible APIdocs
sglang serve NousResearch/Arete-27B --host 0.0.0.0 --port 30000

Needs SGLang’s ROCm build (Instinct MI300-class GPUs).

Chat models that fit the Radeon RX 7900 XTX comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
20.9BA4.2BQ8_0≈13 GBFits in memory~119 tok/sCommercial OK
32.8BQ4_K_M≈22 GBFits in memory~27 tok/sCommercial OK
36BA3BQ4_K_M≈23 GBFits in memory~290 tok/sCommercial OK
30.5BA3BQ5_K_M≈22 GBFits in memory~247 tok/sCommercial OK
24BA2BQ6_K≈20 GBFits in memory~320 tok/sConditions
32.8BQ4_K_M≈22 GBFits in memory~27 tok/sCommercial OK

Other GPUs that run Arete-27B

Frequently asked questions

Can the Radeon RX 7900 XTX run Arete-27B?
Yes. The Radeon RX 7900 XTX runs Arete-27B fully in VRAM at Q5_K_M (about 23 GB of 24 GB), at roughly 27 tokens/s.
How fast does Arete-27B run on the Radeon RX 7900 XTX?
An estimate from memory bandwidth gives about 27 tokens/s at Q5_K_M.
Which quantisation of Arete-27B should I use on the Radeon RX 7900 XTX?
Q5_K_M: the largest one that fits. Expected quality: near-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.