Arao AI
Back to search results

Llama-3.2-3B-Instruct · IQ1_S

Start a discussion
NVIDIA RTX 409024GBStrata v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (IQ1_S) on NVIDIA RTX 4090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

284.1 tok/s

Decode

Decode speed

1,178.93 tok/s

Prefill

Prefill speed

0.55 s

TTFT

Time to first token

4.75 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ3_S Decode 362.35 · Prefill 1574.76 ·
  2. Strata · IQ1_S (current)Decode 284.1 · Prefill 1178.93 ·
  3. Strata · IQ2_XS Decode 281.21 · Prefill 1389.98 ·
  4. llama.cpp · Q8_0 Decode 245.7 · Prefill 1842.8 ·
  5. llama.cpp · Q5_K_M Decode 357.4 · Prefill 2680.5 ·
  6. llama.cpp · Q4_K_M Decode 436.8 · Prefill 3276 ·

Core figures

Decode (avg)
284.1 tok/s
Prefill (avg)
1,178.93 tok/s
TTFT (avg)
0.55 s
VRAM (avg)
4.75 GB
MTP acceptance rate
0.57
TTFB
2.27 GB
Power draw
396.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
IQ1_S
Framework
Strata
Version
v0.28
Context length
16384 tokens
Batch size
512
GPU layers
8
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
4.75 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.6
Power draw
396.9 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

    v0.28 · Ubuntu 22.04 · CUDA 12.6 · 16384 ctx

    284.1 tok/s

    Decode

    1,178.93 tok/s

    Prefill

    0.55 s

    TTFT

    4.75 GB

    VRAM

    0.57

    MTP

    396.9 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=1 running model_id=70 at IQ1_S