Arao AI
Back to search results

Qwen3.8-9B · Q4_K_M

Start a discussion
AMD Radeon RX 7900 XTX24GBOllama v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q4_K_M) on AMD Radeon RX 7900 XTX with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

61.26 tok/s

Decode

Decode speed

253.43 tok/s

Prefill

Prefill speed

0.13 s

TTFT

Time to first token

17.6 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · Q3_K_L Decode 79.57 · Prefill 292.41 ·
  2. vLLM · Q3_K_M Decode 85.52 · Prefill 281.83 ·
  3. Ollama · Q4_K_M (current)Decode 61.26 · Prefill 253.43 ·
  4. Ollama · Q5_K_M Decode 56.51 · Prefill 294.11 ·
  5. llama.cpp · IQ2_M Decode 116.92 · Prefill 403.5 ·
  6. llama.cpp · Q4_K_S Decode 92.32 · Prefill 411.04 ·
  7. vLLM · Q8_0 Decode 60.74 · Prefill 270.33 ·

Core figures

Decode (avg)
61.26 tok/s
Prefill (avg)
253.43 tok/s
TTFT (avg)
0.13 s
VRAM (avg)
17.6 GB
MTP acceptance rate
—
TTFB
0.49 GB
Power draw
201.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q4_K_M
Framework
Ollama
Version
v0.39
Context length
32768 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
AMD Radeon RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
17.6 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.12
CUDA
12.8
Power draw
201.2 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.39 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    61.26 tok/s

    Decode

    253.43 tok/s

    Prefill

    0.13 s

    TTFT

    17.6 GB

    VRAM

    —

    MTP

    201.2 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=11 running model_id=52 at Q4_K_M