Back to search results
iFlytek Spark-X2.5-4B · IQ2_XS
NVIDIA H2097GBStrata v0.51L2 Cross-framework verified
This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (IQ2_XS) on NVIDIA H20 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
273.22 tok/s
Decode
Decode speed
1,069.33 tok/s
Prefill
Prefill speed
0.32 s
TTFT
Time to first token
6.13 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
11 days ago
Last verified
Performance
- llama.cpp · Q5_K_S Decode 116.43 · Prefill 457.51 ·
- Strata · IQ2_XS (current)Decode 273.22 · Prefill 1069.33 ·
Core figures
- Decode (avg)
- 273.22 tok/s
- Prefill (avg)
- 1,069.33 tok/s
- TTFT (avg)
- 0.32 s
- VRAM (avg)
- 6.13 GB
- MTP acceptance rate
- 0.7
- TTFB
- 2.19 GB
- Power draw
- 335.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- iFlytek Spark-X2.5-4B
- Quantization
- IQ2_XS
- Framework
- Strata
- Version
- v0.51
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 15
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA H20
- Nominal VRAM
- 97 GB
- Measured VRAM (avg)
- 6.13 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 335.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.51 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx
273.22 tok/s
Decode
1,069.33 tok/s
Prefill
0.32 s
TTFT
6.13 GB
VRAM
0.7
MTP
335.9 W
Power draw
L2 batch seed 2026-10-24: Strata on hw_id=56 running model_id=75 at IQ2_XS