Arao AI
Back to search results

Kimi-K3 · IQ2_XS

Start a discussion
Intel Arc B58012GBStrata v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Kimi-K3 (IQ2_XS) on Intel Arc B580 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

78.95 tok/s

Decode

Decode speed

342.16 tok/s

Prefill

Prefill speed

2.07 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

Today

Last verified

Performance

  1. llama.cpp · IQ3_S Decode 47.04 · Prefill 172.07 ·
  2. llama.cpp · Q3_K_L Decode 43.5 · Prefill 143.66 ·
  3. Strata · IQ2_XS (current)Decode 78.95 · Prefill 342.16 ·

Core figures

Decode (avg)
78.95 tok/s
Prefill (avg)
342.16 tok/s
TTFT (avg)
2.07 s
VRAM (avg)
1.05 GB
MTP acceptance rate
0.5
TTFB
0.63 GB
Power draw
156.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Kimi-K3
Quantization
IQ2_XS
Framework
Strata
Version
v0.31
Context length
4096 tokens
Batch size
1024
GPU layers
15
Flash Attention
On

Hardware

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

GPU
Intel Arc B580
Nominal VRAM
12 GB
Measured VRAM (avg)
1.05 GB
OS
Windows 11 24H2
Driver
Intel Arc 32.0.101.6552
CUDA
12.4
Power draw
156.1 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.31 · Windows 11 24H2 · CUDA 12.4 · 4096 ctx

    78.95 tok/s

    Decode

    342.16 tok/s

    Prefill

    2.07 s

    TTFT

    1.05 GB

    VRAM

    0.5

    MTP

    156.1 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=94 running model_id=73 at IQ2_XS