Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q6_K

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q6_K) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

175.87 tok/s

Decode

Decode speed

672.51 tok/s

Prefill

Prefill speed

1.8 s

TTFT

Time to first token

8.4 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · Q6_K (current)Decode 175.87 · Prefill 672.51 ·
  2. Ollama · Q3_K_L Decode 237.89 · Prefill 1168.16 ·
  3. vLLM · IQ3_S Decode 253.22 · Prefill 1074.86 ·
  4. Strata · IQ3_S Decode 389.24 · Prefill 2015.9 ·
  5. Strata · Q4_K_S Decode 341.32 · Prefill 1578.68 ·

Core figures

Decode (avg)
175.87 tok/s
Prefill (avg)
672.51 tok/s
TTFT (avg)
1.8 s
VRAM (avg)
8.4 GB
MTP acceptance rate
—
TTFB
1.41 GB
Power draw
237.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q6_K
Framework
vLLM
Version
v0.43
Context length
32768 tokens
Batch size
8
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
AMD Radeon RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
8.4 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
12.4
Power draw
237.4 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

    v0.43 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx

    175.87 tok/s

    Decode

    672.51 tok/s

    Prefill

    1.8 s

    TTFT

    8.4 GB

    VRAM

    —

    MTP

    237.4 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=11 running model_id=70 at Q6_K