Arao AI
Back to search results

Llama-3.2-3B-Instruct · IQ4_XS

Start a discussion
NVIDIA RTX 4080 Super16GBllama.cpp v0.50L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (IQ4_XS) on NVIDIA RTX 4080 Super with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

289.96 tok/s

Decode

Decode speed

1,071.96 tok/s

Prefill

Prefill speed

1.43 s

TTFT

Time to first token

6.76 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS Decode 372.98 · Prefill 1597.99 ·
  2. llama.cpp · IQ4_XS (current)Decode 289.96 · Prefill 1071.96 ·
  3. Strata · FP16 Decode 277.08 · Prefill 1141.1 ·
  4. vLLM · IQ3_S Decode 334.5 · Prefill 1159.32 ·
  5. Strata · Q3_K_L Decode 358.87 · Prefill 1331.79 ·

Core figures

Decode (avg)
289.96 tok/s
Prefill (avg)
1,071.96 tok/s
TTFT (avg)
1.43 s
VRAM (avg)
6.76 GB
MTP acceptance rate
—
TTFB
2.32 GB
Power draw
305.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
IQ4_XS
Framework
llama.cpp
Version
v0.50
Context length
8192 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
NVIDIA RTX 4080 Super
Nominal VRAM
16 GB
Measured VRAM (avg)
6.76 GB
OS
Windows 11 23H2
Driver
572.83
CUDA
12.4
Power draw
305.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.50 · Windows 11 23H2 · CUDA 12.4 · 8192 ctx

    289.96 tok/s

    Decode

    1,071.96 tok/s

    Prefill

    1.43 s

    TTFT

    6.76 GB

    VRAM

    —

    MTP

    305.8 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=20 running model_id=70 at IQ4_XS