Arao AI
Back to search results

Qwen3.5-0.8B · Q5_K_M

Start a discussion
AMD Radeon RX 9070 XT16GBllama.cpp v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q5_K_M) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

182.06 tok/s

Decode

Decode speed

1,000.27 tok/s

Prefill

Prefill speed

0.47 s

TTFT

Time to first token

3.66 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · Q5_K_S Decode 285.41 · Prefill 1428.43 ·
  2. Ollama · FP16 Decode 127.98 · Prefill 427.95 ·
  3. Ollama · Q5_K_S Decode 242.84 · Prefill 980.43 ·
  4. llama.cpp · Q5_K_M (current)Decode 182.06 · Prefill 1000.27 ·
  5. vLLM · IQ3_S Decode 301.46 · Prefill 1013.4 ·

Core figures

Decode (avg)
182.06 tok/s
Prefill (avg)
1,000.27 tok/s
TTFT (avg)
0.47 s
VRAM (avg)
3.66 GB
MTP acceptance rate
—
TTFB
1.46 GB
Power draw
303.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q5_K_M
Framework
llama.cpp
Version
v0.33
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 9070 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
3.66 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
303.3 W

Sources & evidence

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

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

    v0.33 · Ubuntu 24.04 · CUDA N/A · 2048 ctx

    182.06 tok/s

    Decode

    1,000.27 tok/s

    Prefill

    0.47 s

    TTFT

    3.66 GB

    VRAM

    —

    MTP

    303.3 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=16 running model_id=51 at Q5_K_M