Arao AI
Back to search results

Qwen3.5-0.8B · Q4_K_M

Start a discussion
Qualcomm Snapdragon X Elitellama.cpp v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q4_K_M) on Qualcomm Snapdragon X Elite with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

112.42 tok/s

Decode

Decode speed

515.25 tok/s

Prefill

Prefill speed

1.63 s

TTFT

Time to first token

3.48 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_M (current)Decode 112.42 · Prefill 515.25 ·
  2. Ollama · IQ4_XS Decode 117.58 · Prefill 399 ·
  3. Ollama · Q8_0 Decode 69.82 · Prefill 301.4 ·

Core figures

Decode (avg)
112.42 tok/s
Prefill (avg)
515.25 tok/s
TTFT (avg)
1.63 s
VRAM (avg)
3.48 GB
MTP acceptance rate
—
TTFB
0.9 GB
Power draw
19.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.42
Context length
8192 tokens
Batch size
512
GPU layers
20
Flash Attention
On

Hardware

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

GPU
Qualcomm Snapdragon X Elite
Measured VRAM (avg)
3.48 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
19.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.42 · Windows 11 23H2 · CUDA N/A · 8192 ctx

    112.42 tok/s

    Decode

    515.25 tok/s

    Prefill

    1.63 s

    TTFT

    3.48 GB

    VRAM

    —

    MTP

    19.8 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=104 running model_id=51 at Q4_K_M