Arao AI
Back to search results

Qwen3-1.7B · Q4_K_M

Start a discussion
AMD Radeon RX 7900 XTX24GBllama.cpp v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_M) on AMD Radeon RX 7900 XTX with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

178.72 tok/s

Decode

Decode speed

842.7 tok/s

Prefill

Prefill speed

0.98 s

TTFT

Time to first token

5.03 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ3_XS Decode 234.47 · Prefill 1079.52 ·
  2. llama.cpp · Q4_K_M (current)Decode 178.72 · Prefill 842.7 ·
  3. Ollama · Q3_K_M Decode 196.24 · Prefill 705.31 ·
  4. Ollama · Q8_0 Decode 111.35 · Prefill 362.65 ·
  5. Strata · Q4_K_S Decode 249 · Prefill 1211.72 ·

Core figures

Decode (avg)
178.72 tok/s
Prefill (avg)
842.7 tok/s
TTFT (avg)
0.98 s
VRAM (avg)
5.03 GB
MTP acceptance rate
—
TTFB
1.43 GB
Power draw
419.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.38
Context length
4096 tokens
Batch size
256
GPU layers
28
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)
5.03 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.4
Power draw
419.1 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

    v0.38 · Ubuntu 24.04 · CUDA 12.4 · 4096 ctx

    178.72 tok/s

    Decode

    842.7 tok/s

    Prefill

    0.98 s

    TTFT

    5.03 GB

    VRAM

    —

    MTP

    419.1 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=11 running model_id=55 at Q4_K_M