Arao AI
Back to search results

Qwen3.5-0.8B · IQ2_XS

Start a discussion
NVIDIA RTX 409024GBllama.cpp v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ2_XS) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

280.41 tok/s

Decode

Decode speed

1,104.34 tok/s

Prefill

Prefill speed

0.27 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

Today

Last verified

Performance

  1. llama.cpp · IQ2_XS (current)Decode 280.41 · Prefill 1104.34 ·
  2. llama.cpp · Q4_K_M Decode 278.24 · Prefill 916.88 ·
  3. vLLM · IQ3_XS Decode 302.65 · Prefill 1148.6 ·

Core figures

Decode (avg)
280.41 tok/s
Prefill (avg)
1,104.34 tok/s
TTFT (avg)
0.27 s
VRAM (avg)
2.91 GB
MTP acceptance rate
—
TTFB
2.24 GB
Power draw
416.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.34
Context length
4096 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
2.91 GB
OS
macOS 15.0
Driver
560.94
CUDA
12.6
Power draw
416.6 W

Sources & evidence

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

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

    v0.34 · macOS 15.0 · CUDA 12.6 · 4096 ctx

    280.41 tok/s

    Decode

    1,104.34 tok/s

    Prefill

    0.27 s

    TTFT

    2.91 GB

    VRAM

    —

    MTP

    416.6 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=1 running model_id=51 at IQ2_XS