Arao AI
Back to search results

Qwen3.8-9B · Q5_K_M

Start a discussion
AMD Radeon RX 7900 XTX24GBOllama v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q5_K_M) on AMD Radeon RX 7900 XTX with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

56.51 tok/s

Decode

Decode speed

294.11 tok/s

Prefill

Prefill speed

1.47 s

TTFT

Time to first token

19.68 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 Decode 61.26 · Prefill 253.43 ·
  4. Ollama · Q5_K_M (current)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)
56.51 tok/s
Prefill (avg)
294.11 tok/s
TTFT (avg)
1.47 s
VRAM (avg)
19.68 GB
MTP acceptance rate
—
TTFB
0.45 GB
Power draw
249.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q5_K_M
Framework
Ollama
Version
v0.54
Context length
4096 tokens
Batch size
512
GPU layers
33
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)
19.68 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
12.4
Power draw
249.4 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

    v0.54 · Ubuntu 22.04 · CUDA 12.4 · 4096 ctx

    56.51 tok/s

    Decode

    294.11 tok/s

    Prefill

    1.47 s

    TTFT

    19.68 GB

    VRAM

    —

    MTP

    249.4 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=11 running model_id=52 at Q5_K_M