Back to search results

Qwen3.6-27B · Q5_K_S

NVIDIA RTX 309024GBllama.cpp v0.3.0-e0663be2713cL0 Self-reported

This page aggregates 1 real-world runs of Qwen3.6-27B (Q5_K_S) on NVIDIA RTX 3090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

46.57 tok/s

Decode

Decode speed

1,201.22 tok/s

Prefill

Prefill speed

0.1 s

TTFT

Time to first token

21.53 GB

VRAM

VRAM usage

L0 Self-reported

1

Measured runs

1

Independent sources

GitHub

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q5_K_S (current)Decode 46.57 · Prefill 1201.22 ·

Core figures

Decode (avg)
46.57 tok/s
Prefill (avg)
1,201.22 tok/s
TTFT (avg)
0.1 s
VRAM (avg)
21.53 GB
MTP acceptance rate
TTFB
— GB
Power draw
— W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-27B
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.3.0-e0663be2713c
Context length
102400 tokens

Hardware

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

GPU
NVIDIA RTX 3090
Nominal VRAM
24 GB
Measured VRAM (avg)
21.53 GB
OS
Debian GNU/Linux 13 (trixie)
Driver
610.43.02
CUDA
13.3

Get started

Sources & evidence

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

  1. L0 Self-reportedGitHubOriginal link Verified on 2026-09-20

    v0.3.0-e0663be2713c · Debian GNU/Linux 13 (trixie) · CUDA 13.3 · 102400 ctx

    46.57 tok/s

    Decode

    1,201.22 tok/s

    Prefill

    0.1 s

    TTFT

    21.53 GB

    VRAM

    MTP

    W

    Power draw

    run-1 wall= 21.87s ttft= 98ms toks=1000 wall_TPS= 45.72 decode_TPS= 45.92 run-2 wall= 20.93s ttft= 98ms toks=1000 wall_TPS= 47.78 decode_TPS= 48.01 run-1 wall= 11.38s ttft= 10971ms prompt_toks= 13179 PP_tok/s=1201.22