Arao AI
Back to search results

Qwen3.8-9B · IQ2_M

Start a discussion
AMD Radeon RX 7900 XTX24GBllama.cpp v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (IQ2_M) on AMD Radeon RX 7900 XTX with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

116.92 tok/s

Decode

Decode speed

403.5 tok/s

Prefill

Prefill speed

1.06 s

TTFT

Time to first token

11.93 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ2_M (current)Decode 116.92 · Prefill 403.5 ·
  2. llama.cpp · Q4_K_S Decode 92.32 · Prefill 411.04 ·
  3. vLLM · Q8_0 Decode 60.74 · Prefill 270.33 ·

Core figures

Decode (avg)
116.92 tok/s
Prefill (avg)
403.5 tok/s
TTFT (avg)
1.06 s
VRAM (avg)
11.93 GB
MTP acceptance rate
—
TTFB
0.94 GB
Power draw
432.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
IQ2_M
Framework
llama.cpp
Version
v0.20
Context length
2048 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)
11.93 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
432.3 W

Sources & evidence

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

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

    v0.20 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx

    116.92 tok/s

    Decode

    403.5 tok/s

    Prefill

    1.06 s

    TTFT

    11.93 GB

    VRAM

    —

    MTP

    432.3 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=11 running model_id=52 at IQ2_M