Arao AI
Back to search results

Llama-3.2-3B-Instruct · IQ4_XS

Start a discussion
NVIDIA RTX 509032GBvLLM v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (IQ4_XS) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

321.22 tok/s

Decode

Decode speed

1,224.88 tok/s

Prefill

Prefill speed

2.36 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 · Q4_K_S Decode 375.58 · Prefill 1439.62 ·
  2. llama.cpp · Q5_K_S Decode 373.63 · Prefill 1720.71 ·
  3. vLLM · IQ4_XS (current)Decode 321.22 · Prefill 1224.88 ·
  4. vLLM · Q6_K Decode 292.37 · Prefill 1232.31 ·
  5. llama.cpp · Q2_K Decode 325.57 · Prefill 1657.68 ·
  6. Strata · Q4_K_M Decode 367.38 · Prefill 1255.45 ·
  7. Strata · Q5_K_S Decode 289.95 · Prefill 1022.85 ·
  8. llama.cpp · Q8_0 Decode 436.8 · Prefill 3276 ·
  9. llama.cpp · Q5_K_M Decode 635.3 · Prefill 4764.8 ·
  10. llama.cpp · Q4_K_M Decode 776.5 · Prefill 5823.8 ·

Core figures

Decode (avg)
321.22 tok/s
Prefill (avg)
1,224.88 tok/s
TTFT (avg)
2.36 s
VRAM (avg)
6.76 GB
MTP acceptance rate
—
TTFB
2.57 GB
Power draw
410.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
IQ4_XS
Framework
vLLM
Version
v0.30
Context length
16384 tokens
Batch size
32
GPU layers
999
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
6.76 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.4
Power draw
410.1 W

Sources & evidence

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

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

    v0.30 · Windows 11 23H2 · CUDA 12.4 · 16384 ctx

    321.22 tok/s

    Decode

    1,224.88 tok/s

    Prefill

    2.36 s

    TTFT

    6.76 GB

    VRAM

    —

    MTP

    410.1 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=13 running model_id=70 at IQ4_XS