Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q4_K_M

Start a discussion
NVIDIA RTX 5070 Ti16GBStrata v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q4_K_M) on NVIDIA RTX 5070 Ti with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

361.74 tok/s

Decode

Decode speed

1,475.89 tok/s

Prefill

Prefill speed

0.97 s

TTFT

Time to first token

7.27 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · Q4_K_S Decode 228.86 · Prefill 764.69 ·
  2. Strata · Q4_K_M (current)Decode 361.74 · Prefill 1475.89 ·

Core figures

Decode (avg)
361.74 tok/s
Prefill (avg)
1,475.89 tok/s
TTFT (avg)
0.97 s
VRAM (avg)
7.27 GB
MTP acceptance rate
0.66
TTFB
2.89 GB
Power draw
225.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q4_K_M
Framework
Strata
Version
v0.28
Context length
16384 tokens
Batch size
1024
GPU layers
12
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5070 Ti
Nominal VRAM
16 GB
Measured VRAM (avg)
7.27 GB
OS
Ubuntu 22.04
Driver
560.94
CUDA
12.4
Power draw
225.6 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 12.4 · 16384 ctx

    361.74 tok/s

    Decode

    1,475.89 tok/s

    Prefill

    0.97 s

    TTFT

    7.27 GB

    VRAM

    0.66

    MTP

    225.6 W

    Power draw

    L2 batch seed 2026-10-18: Strata on hw_id=17 running model_id=70 at Q4_K_M