Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_XS

Start a discussion
AMD Radeon AI PRO R970032GBllama.cpp v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_XS) on AMD Radeon AI PRO R9700 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

394.48 tok/s

Decode

Decode speed

1,743.78 tok/s

Prefill

Prefill speed

0.97 s

TTFT

Time to first token

2.91 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS (current)Decode 394.48 · Prefill 1743.78 ·
  2. Ollama · IQ1_S Decode 368.92 · Prefill 1396.86 ·
  3. Ollama · Q4_K_S Decode 284.75 · Prefill 1200.05 ·

Core figures

Decode (avg)
394.48 tok/s
Prefill (avg)
1,743.78 tok/s
TTFT (avg)
0.97 s
VRAM (avg)
2.91 GB
MTP acceptance rate
—
TTFB
3.16 GB
Power draw
271.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.48
Context length
16384 tokens
Batch size
256
GPU layers
28
Flash Attention
On

Hardware

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

GPU
AMD Radeon AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
2.91 GB
OS
Windows 11 23H2
Driver
amdgpu 6.10
CUDA
N/A
Power draw
271.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.48 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    394.48 tok/s

    Decode

    1,743.78 tok/s

    Prefill

    0.97 s

    TTFT

    2.91 GB

    VRAM

    —

    MTP

    271.6 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=79 running model_id=51 at IQ2_XS