MiniMax-M2.7-JANGTQ4

⚠️ REQUIRED — jangtq_runtime.safetensors sidecar must be downloaded

Osaurus uses the native Swift JANGTQ runtime. Every JANGTQ bundle on OsaurusAI ships a small jangtq_runtime.safetensors sidecar (~10 KB–~165 KB) alongside the weight shards. The Swift loader will refuse to start with the error

Error: Model '<name>' declares JANGTQ (weight_format: "mxtq") but is
       missing required sidecar file 'jangtq_runtime.safetensors'.
       Re-download the full model or obtain the sidecar from the original
       publisher.

if the file is absent.

If your local copy doesn't have it (older download, partial sync, etc):

hf download OsaurusAI/MiniMax-M2.7-JANGTQ4 jangtq_runtime.safetensors --local-dir <your-dir>

The file holds the deterministic codebooks + Hadamard rotation signs the Swift loader uses to decode *.tq_packed weights. It must match the seed the bundle was quantized with (mxtq_seed=42).

<p align="center"> <a href="https://osaurus.ai"><img src="./osaurus-x-banner.png" alt="Osaurus AI"></a> </p> <h3 align="center">MiniMax M2.7 &mdash; JANGTQ4 (MLX)</h3> <p align="center">TurboQuant codebook quantization of MiniMax's 228B agentic MoE &mdash; routed experts at 4-bit via Lloyd-Max codebooks + Hadamard rotation, attention / embed / shared-expert / lm_head at 8-bit affine. Near-bf16 quality at ~25% of bf16 disk.</p> <p align="center"> <a href="https://osaurus.ai"><img src="https://img.shields.io/badge/Web-osaurus.ai-blue" alt="Website"></a>&nbsp; <a href="https://huggingface.co/OsaurusAI"><img src="https://img.shields.io/badge/HF-OsaurusAI-yellow?logo=huggingface" alt="OsaurusAI"></a> </p>

---

Model Details

What is JANGTQ4?

JANGTQ (JANG TurboQuant) is a codebook-based quantization format for MoE models on Apple Silicon. Routed expert weights stay in a compact codebook + Hadamard-rotated form at runtime — no decompression to affine — and the matmul path uses custom Metal kernels that read packed uint32 weights, look up centroids in a small codebook, and accumulate dot products against a Hadamard-rotated input (QuIP# rotate-input-once math).

JANGTQ4 uses a 16-entry Lloyd-Max codebook per routed expert tensor, which captures the weight distribution near-losslessly. Quality approaches bf16 at ~25% of bf16 disk and runs at the full JANGTQ decode speed. Pick this profile when RAM permits and you want the closest quality to bf16 on Apple Silicon; pick JANGTQ (2-bit) for the smallest footprint.

JANGTQ vs JANGTQ4 vs bf16

Bit Allocation

The routed experts are 98 % of parameters and the natural compression target. Everything else stays at 8-bit affine so the quality-critical hot path runs at full precision.

Important Settings

MiniMax M2.7 is an always-reasoning model. The chat template unconditionally opens <think> at each assistant turn.

Strip <think>…</think> from the response before using the final answer.

Usage

This model requires the jang-tools loader — stock mlx_lm.load() does not recognize weight_format: mxtq. The loader applies Metal kernel monkey-patches at load time (fused gate+up+SwiGLU, gather TQ, multi-block Hadamard, router compile, QKV fusion).

pip install jang-tools

from huggingface_hub import snapshot_download
from jang_tools.load_jangtq import load_jangtq_model
from mlx_lm import generate

model_path = snapshot_download("OsaurusAI/MiniMax-M2.7-JANGTQ4")
model, tokenizer = load_jangtq_model(model_path)

messages = [{"role": "user", "content": "Explain photosynthesis in five sentences."}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)
out = generate(model, tokenizer, prompt, max_tokens=600,
               temperature=1.0, verbose=True)

Swift — Osaurus / MLX Studio

Both clients auto-detect the JANGTQ runtime from jang_config.json and route through the MiniMaxJANGTQModel class. Just load the repo — no extra flags.

What's In This Repo

Parser Capabilities (Tier-1 auto-detected by Osaurus / vmlx)

{
  "reasoning_parser": "qwen3",
  "tool_parser": "minimax",
  "think_in_template": true,
  "supports_tools": true,
  "supports_thinking": true,
  "family": "minimax_m2",
  "modality": "text",
  "cache_type": "kv"
}

<think> and <tool_call> are non-special tokens by design — the application layer parses them. Osaurus and vmlx CapabilityDetector read this block verbatim and wire the qwen3 reasoning parser + minimax tool parser automatically, so streamed responses route reasoning_content and tool_calls into the OpenAI-compatible SSE fields instead of leaking into content.

License

MIT — see LICENSE.

Credits

Created by Jinho Jang — [email protected]

Based on MiniMaxAI's MiniMax M2.7. JANGTQ quantization © JANGQ-AI.