Arao AI
Back to search results

Hy-Memory-30B-A3B · FP16

Start a discussion
NVIDIA RTX Spark128GBllama.cpp v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of Hy-Memory-30B-A3B (FP16) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

42.81 tok/s

Decode

Decode speed

164.71 tok/s

Prefill

Prefill speed

2.94 s

TTFT

Time to first token

110.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

15 days ago

Last verified

Performance

  1. llama.cpp · FP16 (current)Decode 42.81 · Prefill 164.71 ·
  2. llama.cpp · Q5_K_M Decode 67.28 · Prefill 348.21 ·
  3. llama.cpp · Q8_0 Decode 58.7 · Prefill 210.79 ·
  4. Ollama · Q5_K_M Decode 64.27 · Prefill 274.24 ·
  5. Ollama · Q8_0 Decode 46.83 · Prefill 233.52 ·
  6. llama.cpp · IQ4_XS Decode 93.67 · Prefill 407.31 ·
  7. llama.cpp · Q4_K_M Decode 85.75 · Prefill 321.23 ·
  8. Ollama · IQ4_XS Decode 76.19 · Prefill 410.3 ·
  9. Ollama · Q4_K_M Decode 69.54 · Prefill 373.27 ·

Core figures

Decode (avg)
42.81 tok/s
Prefill (avg)
164.71 tok/s
TTFT (avg)
2.94 s
VRAM (avg)
110.2 GB
MTP acceptance rate
—
TTFB
0.34 GB
Power draw
50.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Hy-Memory-30B-A3B
Quantization
FP16
Framework
llama.cpp
Version
v0.28
Context length
16384 tokens
Batch size
512
GPU layers
99
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)
110.2 GB
OS
Ubuntu 24.04
Driver
615.78
CUDA
13.0
Power draw
50.6 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 2026-10-20

    v0.28 · Ubuntu 24.04 · CUDA 13.0 · 16384 ctx

    42.81 tok/s

    Decode

    164.71 tok/s

    Prefill

    2.94 s

    TTFT

    110.2 GB

    VRAM

    —

    MTP

    50.6 W

    Power draw

    L2 batch seed 2026-10-20 (Linux 116GiB unlock): llama.cpp on Spark running model_id=87 at FP16