Arao AI
Back to search results

Qwen3.8-27B · Q5_K_M

Start a discussion
NVIDIA RTX Spark128GBllama.cpp v0.36L2 Cross-framework verified

This page aggregates 2 real-world runs of Qwen3.8-27B (Q5_K_M) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

8.81 tok/s

Decode

Decode speed

37.51 tok/s

Prefill

Prefill speed

2.19 s

TTFT

Time to first token

54.83 GB

VRAM

VRAM usage

L2 Cross-framework verified

2

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · Q5_K_M (current)Decode 8.81 · Prefill 37.51 ·
  2. llama.cpp · Q8_0 Decode 6.42 · Prefill 24.36 ·
  3. Ollama · Q5_K_M Decode 7.6 · Prefill 28.29 ·
  4. Ollama · Q6_K Decode 7.47 · Prefill 38.07 ·
  5. Ollama · Q8_0 Decode 6.14 · Prefill 31.39 ·
  6. llama.cpp · Q4_K_M Decode 10.59 · Prefill 58.05 ·
  7. Ollama · Q4_K_M Decode 9.3 · Prefill 41.72 ·
  8. Ollama · Q4_K_S Decode 9.16 · Prefill 49.98 ·

Core figures

Decode (avg)
8.81 tok/s
Prefill (avg)
37.51 tok/s
TTFT (avg)
2.19 s
VRAM (avg)
54.83 GB
MTP acceptance rate
—
TTFB
0.07 GB
Power draw
72.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-27B
Quantization
Q5_K_M
Framework
llama.cpp
Version
v0.36
Context length
16384 tokens
Batch size
512
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX Spark
Nominal VRAM
128 GB
Measured VRAM (avg)
54.83 GB
OS
Ubuntu 24.04
Driver
615.78
CUDA
13.0
Power draw
76.8 W
Reference price
$2,399 · updated 2026-10-19

Prices are not live; check the store page

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-20

    v0.36 · Ubuntu 24.04 · CUDA 13.0 · 16384 ctx

    9.04 tok/s

    Decode

    44.23 tok/s

    Prefill

    3.06 s

    TTFT

    54.83 GB

    VRAM

    —

    MTP

    76.8 W

    Power draw

    L2 batch seed 2026-10-20 (Linux 116GiB unlock): llama.cpp on Spark running model_id=5 at Q5_K_M
  2. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.39 · Windows 11 24H2 · CUDA 13.0 · 32768 ctx

    8.57 tok/s

    Decode

    30.79 tok/s

    Prefill

    1.32 s

    TTFT

    54.83 GB

    VRAM

    —

    MTP

    68.6 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=110 running model_id=5 at Q5_K_M