Christeck/Qwen3.5-35B-A3B-PACKED-GGUF
AI model by Christeck
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.
A lossless repack of Turboderp's EXL3 trellis codes for Qwen3.5-35B-A3B (MoE, 3B active parameters) into the Packed GGUF format used by the Metal Trellis engine (Apple Silicon / Metal). No retraining, no fine-tuning: the trellis codes are identical to the EXL3 source; only the container changed. The engine is the product. This file is the courtesy copy, published so nobody has to repeat the conversion work (which originally ran on rented Blackwell/A100 hardware). If you want to build your own Packed GGUFs from any EXL3 checkpoint, the instructions live in the Metal Trellis repo. This is not a stock llama.cpp GGUF. It requires the Metal Trellis fork, which decodes the trellis-packed expert weights on the fly with Metal kernels: This model is distributed under the Apache License 2.0, "AS IS", without warranties of any kind. Reempaque sin pérdida de los códigos trellis EXL3 de Turboderp para Qwen3.5-35B-A3B (MoE, 3 mil…
Read the full model card ↗ · Preview checked 2026-11-22T07:41:29.190Z
Inside the original model card — Document outline
- Qwen3.5-35B-A3B — Packed GGUF (EXL3 trellis) for Metal Trellis
- How to run
- Honest measurements (M1 Max, 64 GB)
- Attribution and changes
- Resumen (español)
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
Christeck/Qwen3.5-35B-A3B-PACKED-GGUF is a task-unspecified model repository published by Christeck on Hugging Face. The source reports the trellis library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- trellis
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-22T06:56:28.000Z
- Last modified
- 2026-11-22T06:56:53.000Z
Compatibility and lineage
Reported languages: en, es
Reported base models: Qwen/Qwen3.5-35B-A3B
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 2026-11-22T07:03:33.420Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.