Inkling DSpark Preview is an open-source language model by RadixArk. Features: 1.7b LLM, VRAM: 3.5GB, Context: 1024K, LLM Explorer Score: 0.3.
Custom code Dflash Dspark Feature-extraction Qwen3 Region:us Safetensors Sglang Specforge Speculative-decoding
Model Card on HF 🤗: https://huggingface.co/RadixArk/Inkling-DSpark-Preview
Inkling DSpark Preview Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Inkling DSpark Preview Parameters and Internals
| LLM Name | Inkling DSpark Preview |
| Repository 🤗 | https://huggingface.co/RadixArk/Inkling-DSpark-Preview |
| Model Size | 1.7b |
| Required VRAM | 3.5 GB |
| Updated | 2026-07-23 |
| Maintainer | RadixArk |
| Model Type | qwen3 |
| Model Files | |
| Model Architecture | DSparkDraftModel |
| Context Length | 1048576 |
| Model Max Length | 1048576 |
| Transformers Version | 5.8.1 |
| Vocabulary Size | 201024 |
Rank the Inkling DSpark Preview Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 55346 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a