Arao AI
Back to search results

Qwen3.5-0.8B · IQ4_XS

Start a discussion
NVIDIA RTX 309024GBStrata v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ4_XS) on NVIDIA RTX 3090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

382.98 tok/s

Decode

Decode speed

1,282.3 tok/s

Prefill

Prefill speed

2.28 s

TTFT

Time to first token

3.34 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 352.68 · Prefill 1697.91 ·
  2. llama.cpp · Q3_K_L Decode 315.76 · Prefill 1365.7 ·
  3. Strata · IQ4_XS (current)Decode 382.98 · Prefill 1282.3 ·
  4. Strata · Q3_K_M Decode 336.19 · Prefill 1574.41 ·

Core figures

Decode (avg)
382.98 tok/s
Prefill (avg)
1,282.3 tok/s
TTFT (avg)
2.28 s
VRAM (avg)
3.34 GB
MTP acceptance rate
0.66
TTFB
3.06 GB
Power draw
337.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ4_XS
Framework
Strata
Version
v0.30
Context length
16384 tokens
Batch size
256
GPU layers
12
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
3.34 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.8
Power draw
337.8 W

Sources & evidence

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

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

    v0.30 · Ubuntu 22.04 · CUDA 12.8 · 16384 ctx

    382.98 tok/s

    Decode

    1,282.3 tok/s

    Prefill

    2.28 s

    TTFT

    3.34 GB

    VRAM

    0.66

    MTP

    337.8 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=2 running model_id=51 at IQ4_XS