| --- |
| license: apache-2.0 |
| library_name: mlx |
| tags: |
| - mlx |
| - inkling |
| - moe |
| - text-generation |
| - speech |
| - vision |
| - text |
| - audio |
| base_model: thinkingmachines/Inkling-NVFP4 |
| pipeline_tag: text-generation |
| language: |
| - en |
| --- |
| |
| # Inkling-mlx (4-bit, text backbone) |
|
|
| An **MLX 4-bit** build of the encoder-free **text backbone** of Thinking Machines' **Inkling** |
| (975B-total / 41B-active MoE), for running natively on Apple Silicon with |
| [`mlx-lm`](https://github.com/ml-explore/mlx-lm). |
|
|
| This is created for people using a two Apple Mac Studio M3 Ultra with 192/512 GB. (for one Mac Studio you need 2-bit!) |
|
|
| > **Community note** This is **not fullly numerically-verified** |
| > conversion, shared to see whether anyone can load/run a model this large on Apple |
| > Silicon and to gather feedback. Expect rough edges; please open a discussion with |
| > results (or failures). |
|
|
| ## Notes |
|
|
| - **Memory:** the build is ~**580 GB** on disk (4-bit routed experts + bf16 attention / |
| shared experts / embeddings). Loading it needs roughly that much **unified memory**, beyond |
| any single Mac today (max 512 GB), so realistically it needs distributed/multi-device MLX or |
| a very large box. This is largely a **research artifact**. |
| - **Not fully verified yet:** the custom Inkling forward (factorized attention + short-conv + sigmoid |
| MoE) is a from-reference reimplementation whose logits have **not** been checked against the |
| original. Correctness is unconfirmed. |
|
|
|
|
| ## Provenance |
|
|
| - **Source:** `thinkingmachines/Inkling-NVFP4` (NVFP4) → dequantized → MLX affine **4-bit** |
| (group size 64). Only the routed MoE experts are quantized; everything else is bf16. |
| - NVFP4→INT4 re-quantization, so expect small extra quality loss vs. a BF16-sourced build. |
|
|
| ## Usage (once a loader is available) |
|
|
| ```python |
| from mlx_lm import load, generate |
| model, tokenizer = load("mlx-community/Inkling-NVFP4-mlx-4bit") |
| print(generate(model, tokenizer, prompt="The capital of France is", max_tokens=64)) |
| ``` |
|
|
| > The custom model class lives in the conversion repo (`models/inkling_mlx.py`); until it's |
| > registered in `mlx-lm`, load via that module's `load()`. |
| > |
| > Blog: https://huckiyang.github.io/blog/inkling-audio-design.html |
