--- title: README colorFrom: gray colorTo: gray sdk: static pinned: false --- # OpensourceWTF Model packs for Apple silicon: streaming EXL3 packs for [mlx-serve](https://github.com/ddalcu/mlx-serve), whose experts stream from SSD so a 128 GB Mac can serve models larger than its memory, the Qwen3.8 EXL3 packs, and MTPLX packs. Each group below is a collection. ### [EXL3 streaming packs](https://huggingface.co/collections/OpensourceWTF/exl3-streaming-packs-6aea60540c8cae5e023d0d0c) Packs whose routed experts stream from SSD, for mlx-serve. | Family | Repo | Runtime | Branches | Status | |---|---|---|---|---| | DeepSeek-V4.1-Flash-1017 | [DeepSeek-V4.1-Flash-1017-streaming-repack-exl3](https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-1017-streaming-repack-exl3) | mlx-serve + turboexl3_ds41 (`2.81bpw`), mlx-stream (`2.9bpw`) | `2.81bpw`, `2.9bpw`; `1.68bpw`, `2.25bpw`, `2.68bpw` (testing) | live | | DeepSeek-V4.1-Flash (earlier base) | [DeepSeek-V4.1-Flash-streaming-repack-exl3](https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-streaming-repack-exl3) | mlx-serve + mlx-stream | `3.0bpw` | live | ### [Qwen3.8-Flash-Next · mlx-serve EXL3](https://huggingface.co/collections/OpensourceWTF/qwen38-flash-next-mlx-serve-exl3-6aea5ec8a117ec5c8df4febf) turboderp's EXL3 quants in mlx-serve's layout; the experts load into memory. | Family | Repo | Runtime | Branches | Status | |---|---|---|---|---| | Qwen3.8-Flash-Next | [Qwen3.8-Flash-Next-exl3](https://huggingface.co/OpensourceWTF/Qwen3.8-Flash-Next-exl3) | mlx-serve + turboexl3 | `5.05bpw`, `4.05bpw`, `3.05bpw`, `2.05bpw` | live | ### [GLM-5.x · streaming EXL3](https://huggingface.co/collections/OpensourceWTF/glm-5x-streaming-exl3-6aea5ec99f099b9d0e260292) GLM-5.3 and GLM-5.3-Flash EXL3 packs for mlx-serve + mlx-stream. | Family | Repo | Runtime | Branches | Status | |---|---|---|---|---| | GLM-5.3-Flash | [GLM-5.3-Flash-streaming-repack-exl3-3.05bpw](https://huggingface.co/OpensourceWTF/GLM-5.3-Flash-streaming-repack-exl3-3.05bpw) | mlx-serve + mlx-stream | `main` | live | | GLM-5.3 | [GLM-5.3-streaming-repack-exl3-3.0bpw](https://huggingface.co/OpensourceWTF/GLM-5.3-streaming-repack-exl3-3.0bpw) | mlx-serve + mlx-stream | `main` | live | | GLM-5.3 | [GLM-5.3-streaming-repack-exl3-3.42bpw](https://huggingface.co/OpensourceWTF/GLM-5.3-streaming-repack-exl3-3.42bpw) | mlx-serve + mlx-stream | `main` | live | ### [MTPLX streaming packs](https://huggingface.co/collections/OpensourceWTF/mtplx-streaming-packs-6aea5ec9819dbca9cb7f62c7) Packs for MTPLX on Apple silicon. | Family | Repo | Runtime | Branches | Status | |---|---|---|---|---| | DeepSeek-V4.1-Flash | [DeepSeek-V4.1-Flash-MTPLX-streaming-q2](https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2) | MTPLX | `main` | live | | Hunyuan 3.0 | [Hy3-oQ2e-MTPLX-streaming](https://huggingface.co/OpensourceWTF/Hy3-oQ2e-MTPLX-streaming) | MTPLX | `main` | live | | Kimi K3 | [Kimi-K3-Q2_K-t158-MTPLX-streaming](https://huggingface.co/OpensourceWTF/Kimi-K3-Q2_K-t158-MTPLX-streaming) | MTPLX | `main` | live | | Qwen3.8-Flash-Next | [Qwen3.8-Flash-Next-MTPLX-oQ4-MTP](https://huggingface.co/OpensourceWTF/Qwen3.8-Flash-Next-MTPLX-oQ4-MTP) | MTPLX | `main` | live | | GLM-5.2 | [GLM-5.2-t158-MTPLX-streaming](https://huggingface.co/OpensourceWTF/GLM-5.2-t158-MTPLX-streaming) | MTPLX | `main` | live | ### [mlx-stream and other](https://huggingface.co/collections/OpensourceWTF/mlx-stream-and-other-6aea5ecaa117ec5c8df4fee6) Other packs. | Family | Repo | Runtime | Branches | Status | |---|---|---|---|---| | Beam 1.0 | [Beam-1.0-501B-A23B-NVFP4-q8-mlx-stream](https://huggingface.co/OpensourceWTF/Beam-1.0-501B-A23B-NVFP4-q8-mlx-stream) | mlx-serve + mlx-stream | `main` | live | | MiMo-V2.6-Flash-MOPD | [MiMo-V2.6-Flash-MOPD-fp8res-mlx-stream](https://huggingface.co/OpensourceWTF/MiMo-V2.6-Flash-MOPD-fp8res-mlx-stream) | mlx-serve + mlx-stream | `main` | live | | Muse-Glimmer-30B | [Muse-Glimmer-30B-MLX-q4](https://huggingface.co/OpensourceWTF/Muse-Glimmer-30B-MLX-q4) | MTPLX | `main` | live | | DeepSeek-V4.1-Flash-1017 | [DeepSeek-V4.1-Flash-1017-exl3-2.81bpw](https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-1017-exl3-2.81bpw) | exllamav3 (CUDA), the plain layout | `main` | live | ## Moved - `Qwen3.8-Flash-Next-EXL3-5.05-mlx-serve`, `-4.05-mlx-serve`, `-3.05-mlx-serve` and `-2.05-mlx-serve` → the [`5.05bpw`](https://huggingface.co/OpensourceWTF/Qwen3.8-Flash-Next-exl3/tree/5.05bpw), [`4.05bpw`](https://huggingface.co/OpensourceWTF/Qwen3.8-Flash-Next-exl3/tree/4.05bpw), [`3.05bpw`](https://huggingface.co/OpensourceWTF/Qwen3.8-Flash-Next-exl3/tree/3.05bpw) and [`2.05bpw`](https://huggingface.co/OpensourceWTF/Qwen3.8-Flash-Next-exl3/tree/2.05bpw) branches of [Qwen3.8-Flash-Next-exl3](https://huggingface.co/OpensourceWTF/Qwen3.8-Flash-Next-exl3). Each old repo is a stub. - `DeepSeek-V4.1-Flash-1017-streaming-repack-exl3-2.9bpw` → the [`2.9bpw`](https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-1017-streaming-repack-exl3/tree/2.9bpw) branch of [DeepSeek-V4.1-Flash-1017-streaming-repack-exl3](https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-1017-streaming-repack-exl3). The old repo is a stub. - `Kimi-K3-Q2_K-t158-MTPLX` (the fully resident serialization) was removed to free storage; the supported checkpoint is [Kimi-K3-Q2_K-t158-MTPLX-streaming](https://huggingface.co/OpensourceWTF/Kimi-K3-Q2_K-t158-MTPLX-streaming). The old repo is a stub. - Renamed (the old names redirect): `DeepSeek-V4.1-Flash-1017-exl3` → `DeepSeek-V4.1-Flash-1017-streaming-repack-exl3`; `DeepSeek-V4.1-Flash-streaming-repack-exl3-3.0bpw` → `DeepSeek-V4.1-Flash-streaming-repack-exl3` (branch `3.0bpw`).