Arao AI
Back to search results

Qwen3.8-27B · Q4_K_S

Start a discussion
NVIDIA RTX Spark128GBOllama v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-27B (Q4_K_S) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

9.16 tok/s

Decode

Decode speed

49.98 tok/s

Prefill

Prefill speed

0.55 s

TTFT

Time to first token

46.33 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q5_K_M 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 (current)Decode 9.16 · Prefill 49.98 ·

Core figures

Decode (avg)
9.16 tok/s
Prefill (avg)
49.98 tok/s
TTFT (avg)
0.55 s
VRAM (avg)
46.33 GB
MTP acceptance rate
—
TTFB
0.07 GB
Power draw
78.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-27B
Quantization
Q4_K_S
Framework
Ollama
Version
v0.38
Context length
16384 tokens
Batch size
512
GPU layers
28
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)
46.33 GB
OS
Ubuntu 24.04
Driver
NVIDIA 590.10
CUDA
13.0
Power draw
78.4 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

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.38 · Ubuntu 24.04 · CUDA 13.0 · 16384 ctx

    9.16 tok/s

    Decode

    49.98 tok/s

    Prefill

    0.55 s

    TTFT

    46.33 GB

    VRAM

    —

    MTP

    78.4 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=110 running model_id=5 at Q4_K_S