Arao AI
Back to search results

Llama-3-8B-Instruct · Q4_K_M

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3-8B-Instruct (Q4_K_M) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

95.65 tok/s

Decode

Decode speed

325.43 tok/s

Prefill

Prefill speed

1.27 s

TTFT

Time to first token

15.88 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 · Q4_K_M (current)Decode 95.65 · Prefill 325.43 ·
  2. Ollama · Q5_K_S Decode 74.72 · Prefill 318.2 ·
  3. vLLM · Q6_K Decode 72.29 · Prefill 325.63 ·
  4. Ollama · IQ4_XS Decode 87.11 · Prefill 460.37 ·

Core figures

Decode (avg)
95.65 tok/s
Prefill (avg)
325.43 tok/s
TTFT (avg)
1.27 s
VRAM (avg)
15.88 GB
MTP acceptance rate
—
TTFB
0.77 GB
Power draw
225.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3-8B-Instruct
Quantization
Q4_K_M
Framework
vLLM
Version
v0.48
Context length
8192 tokens
Batch size
32
GPU layers
999
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 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
15.88 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
12.8
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 2026-10-19

    v0.48 · Windows 11 23H2 · CUDA 12.8 · 8192 ctx

    95.65 tok/s

    Decode

    325.43 tok/s

    Prefill

    1.27 s

    TTFT

    15.88 GB

    VRAM

    —

    MTP

    225.6 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=11 running model_id=69 at Q4_K_M