iFlytek Spark-X2.5-4B · IQ3_S
This page aggregates 1 real-world runs of iFlytek Spark-X2.5-4B (IQ3_S) on NVIDIA RTX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
107.47 tok/s
Decode
Decode speed
568.49 tok/s
Prefill
Prefill speed
1.15 s
TTFT
Time to first token
7.64 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
11 days ago
Last verified
Performance
- llama.cpp · Q4_K_M Decode 82.35 · Prefill 342.05 ·
- Ollama · IQ3_S (current)Decode 107.47 · Prefill 568.49 ·
Core figures
- Decode (avg)
- 107.47 tok/s
- Prefill (avg)
- 568.49 tok/s
- TTFT (avg)
- 1.15 s
- VRAM (avg)
- 7.64 GB
- MTP acceptance rate
- —
- TTFB
- 0.86 GB
- Power draw
- 55.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- iFlytek Spark-X2.5-4B
- Quantization
- IQ3_S
- Framework
- Ollama
- Version
- v0.39
- Context length
- 65536 tokens
- Batch size
- 512
- GPU layers
- 20
- Flash Attention
- Off
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)
- 7.64 GB
- OS
- Ubuntu 24.04
- Driver
- 615.78
- CUDA
- 13.0
- Power draw
- 55.6 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
Sources & evidence
1 measured records in total, each traceable to its original source
v0.39 · Ubuntu 24.04 · CUDA 13.0 · 65536 ctx
107.47 tok/s
Decode
568.49 tok/s
Prefill
1.15 s
TTFT
7.64 GB
VRAM
—
MTP
55.6 W
Power draw
L2 batch seed 2026-10-24: Ollama on hw_id=110 running model_id=75 at IQ3_S