Hy-Memory-30B-A3B · Q6_K
This page aggregates 1 real-world runs of Hy-Memory-30B-A3B (Q6_K) on NVIDIA H100 80GB HBM3 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
289.84 tok/s
Decode
Decode speed
1,568.48 tok/s
Prefill
Prefill speed
1.64 s
TTFT
Time to first token
65.1 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- llama.cpp · Q6_K (current)Decode 289.84 · Prefill 1568.48 ·
- vLLM · IQ2_XS Decode 346.16 · Prefill 1601.93 ·
- vLLM · Q5_K_M Decode 299.81 · Prefill 1193.35 ·
Core figures
- Decode (avg)
- 289.84 tok/s
- Prefill (avg)
- 1,568.48 tok/s
- TTFT (avg)
- 1.64 s
- VRAM (avg)
- 65.1 GB
- MTP acceptance rate
- —
- TTFB
- 2.32 GB
- Power draw
- 625.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Hy-Memory-30B-A3B
- Quantization
- Q6_K
- Framework
- llama.cpp
- Version
- v0.25
- Context length
- 2048 tokens
- Batch size
- 256
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA H100 80GB HBM3
- Nominal VRAM
- 80 GB
- Measured VRAM (avg)
- 65.1 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 13.0
- Power draw
- 625.4 W
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
v0.25 · Ubuntu 24.04 · CUDA 13.0 · 2048 ctx
289.84 tok/s
Decode
1,568.48 tok/s
Prefill
1.64 s
TTFT
65.1 GB
VRAM
—
MTP
625.4 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=55 running model_id=87 at Q6_K