Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q4_K_M

Start a discussion
AMD Radeon RX 907016GBllama.cpp v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q4_K_M) on AMD Radeon RX 9070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

313.76 tok/s

Decode

Decode speed

1,093.15 tok/s

Prefill

Prefill speed

2.5 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. llama.cpp · Q4_K_M (current)Decode 313.76 · Prefill 1093.15 ·
  2. llama.cpp · Q4_K_S Decode 290.99 · Prefill 1343.85 ·
  3. vLLM · IQ4_XS Decode 366.03 · Prefill 1680.79 ·
  4. vLLM · Q3_K_S Decode 348.42 · Prefill 1407.74 ·

Core figures

Decode (avg)
313.76 tok/s
Prefill (avg)
1,093.15 tok/s
TTFT (avg)
2.5 s
VRAM (avg)
7.27 GB
MTP acceptance rate
—
TTFB
2.51 GB
Power draw
268.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.42
Context length
16384 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

Hardware

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

GPU
AMD Radeon RX 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
7.27 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
12.6
Power draw
268.9 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

    v0.42 · Ubuntu 22.04 · CUDA 12.6 · 16384 ctx

    313.76 tok/s

    Decode

    1,093.15 tok/s

    Prefill

    2.5 s

    TTFT

    7.27 GB

    VRAM

    —

    MTP

    268.9 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=21 running model_id=70 at Q4_K_M