Jakevin/spark-x2.6-4b-gptq4-mlx
text-generation model by Jakevin
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
MLX quantization of XHToken/Spark-X2.6-4B for Apple Silicon. spark25 is a custom architecture not yet in mlx-lm, so this repo ships the MLX model file spark25.py. runmlx.py registers spark25.py with mlx-lm and calls mlxlm.load / generate. The original modelingspark.py is kept for reference (PyTorch, trustremotecode). Apache-2.0, same as the base model (see LICENSE). KL and PPL: 16 held-out sequences (4,601 predicted positions, full vocabulary) against the MLX bf16 model. These numbers are not comparable with KL/PPL reported by other tools (llama.cpp, exllamav3), which use different chunking and reference…
Read the full model card ↗ · Preview checked 2026-10-30T08:43:33.385Z
Inside the original model card — Document outline
- Spark-X2.6-4B GPTQ 4-bit (MLX)
- Results (measured on an M4 Pro Mac mini, 64 GB)
- Usage
- Limitations
- License
- Comparison chart (all MLX builds of this base model)
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Jakevin/spark-x2.6-4b-gptq4-mlx is a text-generation model repository published by Jakevin on Hugging Face. The source reports the mlx library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- mlx
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 4,112,079,360
- Architecture
- Spark2_5ForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-21T06:37:22.000Z
- Last modified
- 2026-10-21T06:39:02.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: XHToken/Spark-X2.6-4B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-21T06:44:13.178Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.