Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_M

Start a discussion
AMD Radeon RX 9070 GRE12GBllama.cpp v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_M) on AMD Radeon RX 9070 GRE with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

264.62 tok/s

Decode

Decode speed

925.29 tok/s

Prefill

Prefill speed

0.15 s

TTFT

Time to first token

2.97 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_M (current)Decode 264.62 · Prefill 925.29 ·
  2. Strata · IQ1_S Decode 369.89 · Prefill 1215.87 ·

Core figures

Decode (avg)
264.62 tok/s
Prefill (avg)
925.29 tok/s
TTFT (avg)
0.15 s
VRAM (avg)
2.97 GB
MTP acceptance rate
—
TTFB
2.12 GB
Power draw
318.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_M
Framework
llama.cpp
Version
v0.23
Context length
16384 tokens
Batch size
512
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 RX 9070 GRE
Nominal VRAM
12 GB
Measured VRAM (avg)
2.97 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
N/A
Power draw
318.5 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

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

    264.62 tok/s

    Decode

    925.29 tok/s

    Prefill

    0.15 s

    TTFT

    2.97 GB

    VRAM

    —

    MTP

    318.5 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=32 running model_id=51 at IQ2_M