Arao AI
Back to search results

Qwen3-Coder-Next · IQ2_XS

Start a discussion
Intel Arc A770 16GB16GBOllama v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ2_XS) on Intel Arc A770 16GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

65.52 tok/s

Decode

Decode speed

349.07 tok/s

Prefill

Prefill speed

2.42 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. vLLM · IQ3_S Decode 59.18 · Prefill 211.63 ·
  2. vLLM · Q4_K_S Decode 48.96 · Prefill 207.46 ·
  3. Ollama · IQ2_XS (current)Decode 65.52 · Prefill 349.07 ·
  4. Ollama · IQ3_XS Decode 57.03 · Prefill 252.47 ·

Core figures

Decode (avg)
65.52 tok/s
Prefill (avg)
349.07 tok/s
TTFT (avg)
2.42 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.52 GB
Power draw
151 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
IQ2_XS
Framework
Ollama
Version
v0.21
Context length
16384 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

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

GPU
Intel Arc A770 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
1.05 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
151 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

    v0.21 · Ubuntu 24.04 · CUDA 12.6 · 16384 ctx

    65.52 tok/s

    Decode

    349.07 tok/s

    Prefill

    2.42 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    151 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=97 running model_id=58 at IQ2_XS