Spark-X2.6-1.7B WebGPU Runtime

Packed Q4 weights and tokenizer for the model-specific WebGPU runtime in mohdmahmodi/Spark-X2.6-1.7B-WebGPU.

The bundle is produced by tools/pack_weights.py from the official mohdmahmodi/Spark-X2.6-1.7B-ONNX-WebGPU Q4f16 export. Quantized payloads are copied byte-for-byte; nothing is requantized.

Contents

  • runtime/manifest.json — tensor offsets, layer plan, KV capacities
  • runtime/layer_00.bin … runtime/layer_27.bin — per-layer q4/q8 tensors
  • runtime/lm_head_0.bin … runtime/lm_head_3.bin — tied embedding/lm_head q8 chunks
  • runtime/lm_head_scales.bin
  • runtime/rope.bin, runtime/final_norm.bin
  • runtime/pack-report.json — SHA-256 of every packed file
  • tokenizer.json, tokenizer_config.json, generation_config.json

The app loads this repository at:

https://huggingface.co/leventkoldas/Spark-X2.6-1.7B-WebGPU-Runtime/resolve/main

and reads runtime/manifest.json, then the weight files and tokenizer relative to that base.

Model

  • 28 layers, hidden 2048, intermediate 6656
  • 8 query heads, 2 KV heads, head dimension 256
  • 131,072 vocabulary, tied embedding/lm_head
  • 512-token sliding window on 21 layers; full attention on 7
  • 32,768-token context
  • q4f16 runtime requires shader-f16
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for leventkoldas/Spark-X2.6-1.7B-WebGPU-Runtime

Finetuned
(5)
this model

Space using leventkoldas/Spark-X2.6-1.7B-WebGPU-Runtime 1