Spark X2.5 1.7B
Parameters
1.7B
Context Length
1.05M
Modality
Text
Architecture
Dense
License
Apache 2.0
Release Date
24 Aug 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Self-hosted only
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
1x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
1,048,576 tokens
Consumer
4x RTX 4090
24GB VRAM
Datacenter
1x NVIDIA A100
80GB VRAM
Apple Silicon
1x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for Spark X2.5 1.7B available.
Rankings
Overall Rank
-
Coding Rank
-
About Spark X2.5 1.7B
Spark X2.5 1.7B is an ultra-lightweight open-weights model tailored for mobile and on-device text generation. It balances minimal latency and low memory footprint with solid general-domain understanding.
Technical Specifications
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
8
Key-Value Heads
2
Attention Head Dimension
256
Position Embedding
ROPE
RoPE Theta
5,000,000
Sliding Window Attention
Yes
Sliding Window Size
512
Sliding Window Ratio
75.0%
Linear Attention
No
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
GELU
Dimensions
Hidden Dimension Size
2,048
Number of Layers
28
FFN Intermediate Size (Dense)
6,656
Multi-Token Prediction Heads
-
Tokenizer
Vocabulary Size
131,072
Resources
About Muse Spark
The Muse Spark model family developed by Thinking Machine Labs.