---
type: "post"
id: "community-mlx-quant-fits-nanbeige4-3-33b-into-c49936"
slug: "community-mlx-quant-fits-nanbeige4-3-33b-into-c49936"
title: "Community MLX quant fits Nanbeige4.3-33B into 15.7 GiB for 24 GB Apple Silicon Macs"
description: "Hugging Face user alexwengg has published Nanbeige4.3-33B-MLX-mixed-3-4-6bit, an MLX quantization of the Apache 2.0 Nanbeige4.3-33B model."
retrieval_nugget: "Hugging Face user alexwengg has published Nanbeige4.3-33B-MLX-mixed-3-4-6bit, an MLX quantization of the Apache 2.0 Nanbeige4.3-33B model."
published_at: "2026-10-26"
updated_at: "2026-10-26"
record_date: "2026-10-26"
date_kind: "published_at"
topics: ["local-models","models","inference"]
entities: ["Nanbeige4.3-33B","Nanbeige","MLX","alexwengg","Hugging Face"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "A community MLX quantization of Nanbeige4.3-33B is said to fit in 15.7 GiB for 24 GB Apple Silicon Macs; prior MLX release coverage concerned Qwen3.8-27B."
prior_refs: ["memory:5d88c1ac-698c-8fd9-a612-47a0ad3efe83","memory:0efd16bc-e919-8bc6-a522-239f013cebf3","memory:07c6ed0e-7b38-8e38-af41-8191afff5dc4"]
source_url: "https://huggingface.co/alexwengg/Nanbeige4.3-33B-MLX-mixed-3-4-6bit"
source_urls: ["https://huggingface.co/alexwengg/Nanbeige4.3-33B-MLX-mixed-3-4-6bit"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:community-mlx-quant-fits-nanbeige4-3-33b-into-c49936"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/community-mlx-quant-fits-nanbeige4-3-33b-into-c49936/","markdown":"https://newruntime.com/posts/community-mlx-quant-fits-nanbeige4-3-33b-into-c49936.md","json":"https://newruntime.com/posts/community-mlx-quant-fits-nanbeige4-3-33b-into-c49936.json"}
---

# Community MLX quant fits Nanbeige4.3-33B into 15.7 GiB for 24 GB Apple Silicon Macs

## Retrieval answer

Hugging Face user alexwengg has published Nanbeige4.3-33B-MLX-mixed-3-4-6bit, an MLX quantization of the Apache 2.0 Nanbeige4.3-33B model.

Hugging Face user alexwengg has published Nanbeige4.3-33B-MLX-mixed-3-4-6bit, an MLX quantization of the Apache 2.0 Nanbeige4.3-33B model. The repository is public, ungated, tagged for MLX and Apple Silicon, and lists a total size of 15.7 GiB.

The mixed layout uses 3-bit weights for MLP gate and up projections, 4-bit weights for attention, down_proj, and embeddings, and 6-bit weights for lm_head. The author says it was made from BF16 weights and can be served with mlx_lm.server as an OpenAI-compatible endpoint.

In the repository description, the author reports roughly 15-16.5 decode tokens per second and about 17 GB peak memory on an M5 Pro with 24 GB of memory. They also report seven passes from eight LeetCode-style smoke tests and a sandboxed terminal-agent run that fixed three bugs in a small repository.

The page does not provide independent benchmarks, reproducible test artifacts, comparisons under controlled settings, or evidence that the reported agent result generalizes beyond the stated small repository.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Local Models](https://newruntime.com/topics/local-models.md): Explore the local-models topic hub.
- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- topic hub: [Inference](https://newruntime.com/topics/inference.md): Explore the inference topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)