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.

empero-ai logo

Can the Radeon RX 9070 XT run Qwen3.8-4B-Distill?

Qwen3.8-4B-Distill·4.7B·Radeon RX 9070 XT·16 GB VRAM

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

Yes. The Radeon RX 9070 XT runs Qwen3.8-4B-Distill fully in VRAM at FP16 / BF16 (about 10.0 GB of 16 GB), at roughly 38 tokens/s.

best quant
FP16 / BF16
needs
10.0 GB
usable
16 GB
est. speed
~38 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Qwen3.8-4B-Distill page →

Every quantisation of Qwen3.8-4B-Distill on the Radeon RX 9070 XT

QuantQualityMemoryFitSpeed
Q2_K Heavy loss3.4 GBfits~230 tok/s
Q3_K_M Noticeable loss3.8 GBfits~155 tok/s
Q4_K_M Small loss4.2 GBfits~125 tok/s
Q5_K_M Near-lossless4.6 GBfits~106 tok/s
Q6_K Near-lossless5.0 GBfits~92 tok/s
Q8_0 Lossless6.0 GBfits~71 tok/s
FP16 / BF16 pickLossless10.0 GBfits~38 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 Qwen3.8-4B-Distill on the Radeon RX 9070 XT

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

Ollama · BF16 straight from Hugging Facedocs
ollama run hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:BF16
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/empero-ai/Qwen3.8-4B-Distill-GGUF:BF16

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 empero-ai/Qwen3.8-4B-Distill-GGUF:BF16

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 empero-ai/Qwen3.8-4B-Distill-GGUF:BF16 --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 empero-ai/Qwen3.8-4B-Distill-GGUF@BF16

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

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve empero-ai/Qwen3.8-4B-Distill

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 empero-ai/Qwen3.8-4B-Distill --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 empero-ai/Qwen3.8-4B-Distill --host 0.0.0.0 --port 30000

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

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="empero-ai/Qwen3.8-4B-Distill", 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
4BQ8_0≈5.8 GBFits in memory~82 tok/sCommercial OK
3.2BQ8_0≈4.7 GBFits in memory~103 tok/sConditions
8BQ8_0≈9.8 GBFits in memory~41 tok/sConditions
3.8BQ8_0≈5.5 GBFits in memory~86 tok/sCommercial OK
4.1BQ8_0≈5.9 GBFits in memory~81 tok/sCommercial OK
4BQ8_0≈5.8 GBFits in memory~82 tok/sCommercial OK

Other GPUs that run Qwen3.8-4B-Distill

Frequently asked questions

Can the Radeon RX 9070 XT run Qwen3.8-4B-Distill?
Yes. The Radeon RX 9070 XT runs Qwen3.8-4B-Distill fully in VRAM at FP16 / BF16 (about 10.0 GB of 16 GB), at roughly 38 tokens/s.
How fast does Qwen3.8-4B-Distill run on the Radeon RX 9070 XT?
An estimate from memory bandwidth gives about 38 tokens/s at FP16 / BF16.
Which quantisation of Qwen3.8-4B-Distill 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.