Back to search results
iFlytek Spark-X2.5-4B · IQ2_XS
Apple M5 Ultra512GBOllama v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (IQ2_XS) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
337.8 tok/s
Decode
Decode speed
1,438.9 tok/s
Prefill
Prefill speed
1.29 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 · IQ2_M Decode 381.7 · Prefill 1687.3 ·
- Ollama · IQ2_XS (current)Decode 337.8 · Prefill 1438.9 ·
Core figures
- Decode (avg)
- 337.8 tok/s
- Prefill (avg)
- 1,438.9 tok/s
- TTFT (avg)
- 1.29 s
- VRAM (avg)
- 6.13 GB
- MTP acceptance rate
- —
- TTFB
- 2.7 GB
- Power draw
- 122.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- iFlytek Spark-X2.5-4B
- Quantization
- IQ2_XS
- Framework
- Ollama
- Version
- v0.44
- Context length
- 8192 tokens
- Batch size
- 256
- 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
- Apple M5 Ultra
- Nominal VRAM
- 512 GB
- Measured VRAM (avg)
- 6.13 GB
- OS
- macOS 26.1
- Power draw
- 122.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · macOS 26.1 · 8192 ctx
337.8 tok/s
Decode
1,438.9 tok/s
Prefill
1.29 s
TTFT
6.13 GB
VRAM
—
MTP
122.4 W
Power draw
L2 batch seed 2026-10-24: Ollama on hw_id=29 running model_id=75 at IQ2_XS