Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_M

Start a discussion
AMD Radeon RX 907016GBvLLM v0.36L2 Cross-framework verified

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

325.3 tok/s

Decode

Decode speed

1,252.35 tok/s

Prefill

Prefill speed

0.8 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 · Q3_K_S Decode 282.09 · Prefill 1248.73 ·
  2. llama.cpp · Q4_K_M Decode 250.59 · Prefill 955.15 ·
  3. Ollama · IQ1_S Decode 353.51 · Prefill 1875.31 ·
  4. llama.cpp · Q3_K_L Decode 236.42 · Prefill 1273.33 ·
  5. vLLM · IQ1_S Decode 361.98 · Prefill 1724.43 ·
  6. vLLM · IQ2_M (current)Decode 325.3 · Prefill 1252.35 ·

Core figures

Decode (avg)
325.3 tok/s
Prefill (avg)
1,252.35 tok/s
TTFT (avg)
0.8 s
VRAM (avg)
2.97 GB
MTP acceptance rate
—
TTFB
2.6 GB
Power draw
238.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_M
Framework
vLLM
Version
v0.36
Context length
32768 tokens
Batch size
16
GPU layers
999
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
Nominal VRAM
16 GB
Measured VRAM (avg)
2.97 GB
OS
Windows 11 23H2
Driver
amdgpu 6.10
CUDA
N/A
Power draw
238.4 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

    v0.36 · Windows 11 23H2 · CUDA N/A · 32768 ctx

    325.3 tok/s

    Decode

    1,252.35 tok/s

    Prefill

    0.8 s

    TTFT

    2.97 GB

    VRAM

    —

    MTP

    238.4 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=21 running model_id=51 at IQ2_M