Arao AI
Back to search results

Qwen3-Coder-Next · Q4_K_S

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBllama.cpp v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (Q4_K_S) on NVIDIA Jetson AGX Orin 64GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

56.6 tok/s

Decode

Decode speed

223.69 tok/s

Prefill

Prefill speed

1.86 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 · Q4_K_S (current)Decode 56.6 · Prefill 223.69 ·
  2. Ollama · Q3_K_M Decode 54.87 · Prefill 250.05 ·

Core figures

Decode (avg)
56.6 tok/s
Prefill (avg)
223.69 tok/s
TTFT (avg)
1.86 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.45 GB
Power draw
48 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.27
Context length
8192 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

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

GPU
NVIDIA Jetson AGX Orin 64GB
Nominal VRAM
64 GB
Measured VRAM (avg)
1.05 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
48 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

    v0.27 · JetPack 6.0 · CUDA 12.6 · 8192 ctx

    56.6 tok/s

    Decode

    223.69 tok/s

    Prefill

    1.86 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    48 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=76 running model_id=58 at Q4_K_S