Models / Spark-X2.5generated from capability-matrix.json
Spark-X2.5
XHToken's Spark-X2.5, 1.7B and 4B.
chatsafetensors
Get it
goinfer can't fetch this one yet. Download the safetensors folder with your usual tool, then point goinfer at it.
goinfer-serve -model ./path/to/checkpoint-folderWhat hasn't been shown
- Runs on the CPU only today. Not eligible to live on a GPU.
- goinfer can't download it for you: this family only loads from safetensors, which come as several files. That's planned (checkpoint fetch, P1–P9).
- No vetted checkpoint, so there's no fit verdict, no speed and no tool-calling result for this family.
How sure we are
Against the released model100.0%
picks the same next token as HuggingFace
1.00000
closest the raw scores get at their worst position (cosine, 1.00000 is identical; bar starts at 0.95)
full-oracle 100.0%/1.00000 · what parity-gated means
Measured speed · decode, tokens per second
not measured — no vetted checkpoint to measure
Architecture, for the curious
- model_type
- spark2_5
- design
- softmax-GQA
- experts
- dense
- attention window
- interleave
- QK-norm
- no
- RoPE
- partial
- norm
- RMSNorm, pre-norm
- activation
- GELU (gated)
- tied head
- no
- modality
- text
- GPU-resident
- no
registry description: XHToken Spark-X2.5 (1.7B/4B): fused QKV, sigmoid head-wise attention output gate, 1:3 sliding:full interleave with layer-dependent partial RoPE, gated exact-GELU MLP