Arao AI
Back to search results

Qwen3.5-0.8B · IQ3_XS

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_XS) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

312.18 tok/s

Decode

Decode speed

1,202.88 tok/s

Prefill

Prefill speed

0.28 s

TTFT

Time to first token

3.14 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q3_K_M Decode 251.67 · Prefill 1158.4 ·
  2. vLLM · IQ3_XS (current)Decode 312.18 · Prefill 1202.88 ·
  3. vLLM · Q6_K Decode 198.86 · Prefill 984.35 ·

Core figures

Decode (avg)
312.18 tok/s
Prefill (avg)
1,202.88 tok/s
TTFT (avg)
0.28 s
VRAM (avg)
3.14 GB
MTP acceptance rate
—
TTFB
2.5 GB
Power draw
411.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ3_XS
Framework
vLLM
Version
v0.53
Context length
4096 tokens
Batch size
16
GPU layers
999
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 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
3.14 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.6
Power draw
411.7 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

    v0.53 · Ubuntu 22.04 · CUDA 12.6 · 4096 ctx

    312.18 tok/s

    Decode

    1,202.88 tok/s

    Prefill

    0.28 s

    TTFT

    3.14 GB

    VRAM

    —

    MTP

    411.7 W

    Power draw

    L2 batch seed 2026-10-10: vLLM on hw_id=11 running model_id=51 at IQ3_XS