Arao AI
Back to search results

Qwen3-Coder-Next · Q3_K_L

Start a discussion
Qualcomm Snapdragon X Elitellama.cpp v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q3_K_L) on Qualcomm Snapdragon X Elite with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

48.96 tok/s

Decode

Decode speed

229.97 tok/s

Prefill

Prefill speed

0.55 s

TTFT

Time to first token

1.05 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 · Q3_K_L (current)Decode 48.96 · Prefill 229.97 ·
  2. Ollama · IQ2_M Decode 54.16 · Prefill 255.41 ·

Core figures

Decode (avg)
48.96 tok/s
Prefill (avg)
229.97 tok/s
TTFT (avg)
0.55 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.39 GB
Power draw
28.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
Q3_K_L
Framework
llama.cpp
Version
v0.33
Context length
16384 tokens
Batch size
512
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 X Elite
Measured VRAM (avg)
1.05 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
28.3 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

    v0.33 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    48.96 tok/s

    Decode

    229.97 tok/s

    Prefill

    0.55 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    28.3 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=104 running model_id=58 at Q3_K_L