サイト内検索
AI モデル 51
- Muse-Glimmer-30B-MLX-4bit↗
TensorFold
- Qwen3.8-Flash-Next-MLX-8bit-MTP↗
TensorFold
- Qwen3.8-Flash-Next-MLX-4bit-MTP↗
TensorFold
A uniform 4-bit MLX conversion of Qwen/Qwen3.8-Flash-Next , rebuilt directly from the official BF16 checkpoint with the model's native MTP draft block preserved. This repository contains the standard uniform 4-bit release. Eligible language-model and native-MTP modules use MLX affine quantisation at group size 32. Multimodal modules and MoE router gates remain in BF16. Group size 32 also covers the model's 160-wide hashed n-gram embedding tables. The upstream tokenizer, chat template, vision processor, generation configuration, licence, and native MTP configuration are retained.
- GLM-5.3-EXL3-2.75bpw-TensorFold↗
Mia-AiLab
- Qwen3.8-Flash-Next-MLX-oQ4↗
TensorFold
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bit↗
TensorFold
A native Apple-silicon conversion of nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 , quantized with stock 4-bit affine weights and packaged for MLX-LM and oMLX. This repository contains a stock 4-bit affine MLX conversion of NVIDIA Nemotron 3.5 Lightning. The source is a 30B-total / 3B-active hybrid mixture-of-experts model that interleaves Mamba-2, sparse MoE, and attention layers. The upstream tokenizer, chat template, and generation configuration are preserved. The decode figure is the median of three greedy 256-token runs after a 32-token Metal-kernel warm-up. It is a practical local reference, not a controlled cross-platform benchmark. Prompt length, context growth, sampler settings, memory pressure, thermal state, and MLX/oMLX versions can materially change performance.
- Qwen3.8-Flash-Next-MLX-oQ2↗
TensorFold
- Qwen3.8-27B-MLX-8bit↗
TensorFold
- Qwen3.8-Flash-Next-Coder-cut240↗
Schiltmans
ISTA-DASLab's IQ1_M Coder GGUF of Qwen3.8-Flash-Next (ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF at 5348543e) with 768 of its 12,288 routed experts removed, served through MLX as an OpenAI-compatible endpoint for coding agents. Each layer keeps 185 to 255 of 256 routed experts, 240 on average; kept tensors are byte for byte as published. This repository is the model folder and its runner in one; the runtime is a TensorFold fork that reads the GGUF tensors in place through mlx-kquant. The fork builds on TensorFold 0.3.4 (MIT) and carries its Python engine, which upstream later replaced with a native one. `DRAFTING=off ./serve.sh` turns drafting off and keeps the disconnect and title behaviour. Some `evidence/` pages were measured with drafting off and without the disconnect and title behaviour; each says which. Requires an Apple Silicon Mac with 48 GB (for 24 GB and 32 GB Macs, see below) and macOS 26 or later (measured on an M4 Pro), about 62 GB of free disk (57 GB model files, 2.2 GB head, about 1 GB environment), git and uv (the download below uses `uvx`; `install.sh` also works with python3.11). Close memory-heavy apps first: `serve.sh` will not start if macOS reports memory pressure or has less than an estimated 36 GB free or held by cached files. This is a startup check; it does not guarantee that memory will suffice later.
- Qwen3.8-Flash-Next-MLX-oQ3-MTP↗
TensorFold