Arao AI
Back to search results

Qwen3.5-0.8B · Q4_K_M

Start a discussion
Qualcomm Snapdragon 7 Gen 4llama.cpp v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q4_K_M) on Qualcomm Snapdragon 7 Gen 4 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

83.77 tok/s

Decode

Decode speed

313.94 tok/s

Prefill

Prefill speed

1.8 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 83.77 · Prefill 313.94 ·
  2. Ollama · IQ2_M Decode 122.21 · Prefill 586.2 ·
  3. Ollama · Q6_K Decode 67.49 · Prefill 328.96 ·

Core figures

Decode (avg)
83.77 tok/s
Prefill (avg)
313.94 tok/s
TTFT (avg)
1.8 s
VRAM (avg)
3.48 GB
MTP acceptance rate
—
TTFB
0.67 GB
Power draw
19.3 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
v0.46
Context length
16384 tokens
Batch size
256
GPU layers
99
Flash Attention
On

Hardware

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

GPU
Qualcomm Snapdragon 7 Gen 4
Measured VRAM (avg)
3.48 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
19.3 W

Sources & evidence

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

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

    v0.46 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    83.77 tok/s

    Decode

    313.94 tok/s

    Prefill

    1.8 s

    TTFT

    3.48 GB

    VRAM

    —

    MTP

    19.3 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=105 running model_id=51 at Q4_K_M