Update README.md

README.md

@@ -32,4 +32,13 @@ High-quality, Apple-Silicon–optimized **MLX** builds, tools, and evals — foc
 | [halley-ai/gpt-oss-120b-MLX-8bit-gs32](https://huggingface.co/halley-ai/gpt-oss-120b-MLX-8bit-gs32) | Q8 / 32 | ~63.42 GB | Reference int8; stable and simple to use. |
 | [halley-ai/gpt-oss-120b-MLX-bf16](https://huggingface.co/halley-ai/gpt-oss-120b-MLX-bf16) | bf16 | ~65.28 GB | Non-quantized reference for evaluation/ground truth. |
 
+### Qwen3-Next-80B-A3B-Instruct (MLX)
+
+| Repo | Bits/GS | Footprint | Notes |
+|---|---:|---:|---|
+| [halley-ai/Qwen3-Next-80B-A3B-Instruct-MLX-6bit-gs64](https://huggingface.co/halley-ai/Qwen3-Next-80B-A3B-Instruct-MLX-6bit-gs64) | Q6 / 64 | ~64.92 GB | Quality pick; matched bf16 on our PPL run (5.14). |
+| [halley-ai/Qwen3-Next-80B-A3B-Instruct-MLX-5bit-gs32](https://huggingface.co/halley-ai/Qwen3-Next-80B-A3B-Instruct-MLX-5bit-gs32) | Q5 / 32 | ~59.86 GB | Balanced; near‑par PPL (5.20) and strong deterministic math. |
+
+Perplexity reported with our fast preset on WikiText‑2 (raw, test). See repository docs for exact commands.
+
 **Format:** MLX (not GGUF). For Linux/Windows or non-MLX stacks, use a GGUF build with llama.cpp.