Arao AI
Back to search results

Qwen3.8-9B · Q3_K_L

Start a discussion
AMD Radeon RX 7900 XTX24GBllama.cpp v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_L) on AMD Radeon RX 7900 XTX with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

79 tok/s

Decode

Decode speed

351.53 tok/s

Prefill

Prefill speed

0.12 s

TTFT

Time to first token

15.71 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_L (current)Decode 79 · Prefill 351.53 ·
  2. Ollama · Q3_K_S Decode 81.43 · Prefill 433.18 ·
  3. Ollama · Q8_0 Decode 45.02 · Prefill 207.48 ·
  4. vLLM · Q3_K_L Decode 79.57 · Prefill 292.41 ·
  5. vLLM · Q3_K_M Decode 85.52 · Prefill 281.83 ·
  6. Ollama · Q4_K_M Decode 61.26 · Prefill 253.43 ·
  7. Ollama · Q5_K_M Decode 56.51 · Prefill 294.11 ·
  8. llama.cpp · IQ2_M Decode 116.92 · Prefill 403.5 ·
  9. llama.cpp · Q4_K_S Decode 92.32 · Prefill 411.04 ·
  10. vLLM · Q8_0 Decode 60.74 · Prefill 270.33 ·

Core figures

Decode (avg)
79 tok/s
Prefill (avg)
351.53 tok/s
TTFT (avg)
0.12 s
VRAM (avg)
15.71 GB
MTP acceptance rate
—
TTFB
0.63 GB
Power draw
211.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q3_K_L
Framework
llama.cpp
Version
v0.35
Context length
2048 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

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)
15.71 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
12.8
Power draw
211.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.35 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx

    79 tok/s

    Decode

    351.53 tok/s

    Prefill

    0.12 s

    TTFT

    15.71 GB

    VRAM

    —

    MTP

    211.6 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=11 running model_id=52 at Q3_K_L