Back to search results
iFlytek Spark-X2.5-4B · Q2_K
Apple M5 Max128GBOllama v0.42L2 Cross-framework verified
This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (Q2_K) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
217.16 tok/s
Decode
Decode speed
1,089.96 tok/s
Prefill
Prefill speed
2.06 s
TTFT
Time to first token
6.72 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 · Q3_K_S Decode 215.47 · Prefill 840.6 ·
- Ollama · Q2_K (current)Decode 217.16 · Prefill 1089.96 ·
Core figures
- Decode (avg)
- 217.16 tok/s
- Prefill (avg)
- 1,089.96 tok/s
- TTFT (avg)
- 2.06 s
- VRAM (avg)
- 6.72 GB
- MTP acceptance rate
- —
- TTFB
- 1.74 GB
- Power draw
- 68.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- iFlytek Spark-X2.5-4B
- Quantization
- Q2_K
- Framework
- Ollama
- Version
- v0.42
- Context length
- 8192 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
- Apple M5 Max
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 6.72 GB
- OS
- macOS 26.1
- Power draw
- 68.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.42 · macOS 26.1 · 8192 ctx
217.16 tok/s
Decode
1,089.96 tok/s
Prefill
2.06 s
TTFT
6.72 GB
VRAM
—
MTP
68.7 W
Power draw
L2 batch seed 2026-10-24: Ollama on hw_id=28 running model_id=75 at Q2_K