Add MTP drafter usage instructions

README.md

@@ -42,6 +42,35 @@ mlx_lm.generate --model hermitdave/Agnes-3.0-Flash-MLX-6bit --prompt "Hello" --m
 
 Drop the folder under `~/.lmstudio/models/hermitdave/` in LM Studio and it appears as a `qwen3_5` model.
 
+## Speculative decoding with MTP drafter
+
+A companion MTP drafter is available for speculative decoding (up to 2× faster generation):
+
+```bash
+pip install mlx-vlm
+python -m mlx_vlm.server \
+    --model hermitdave/Agnes-3.0-Flash-MLX-6bit \
+    --draft-model hermitdave/Agnes-3.0-Flash-MTP-drafter
+```
+
+Or with the Python API:
+
+```python
+from mlx_lm import load
+from mlx_vlm.speculative.drafters.qwen3_5_mtp.config import Qwen3_5MTPConfig
+from mlx_vlm.speculative.drafters.qwen3_5_mtp.qwen3_5_mtp import Qwen3_5MTPDraftModel
+import json, mlx.core as mx, safetensors.torch
+
+base_model, tokenizer = load("hermitdave/Agnes-3.0-Flash-MLX-6bit")
+config = Qwen3_5MTPConfig.from_dict(json.load(open("path/to/Agnes-3.0-Flash-MTP-drafter/config.json")))
+mtp = Qwen3_5MTPDraftModel(config)
+weights = safetensors.torch.load_file("path/to/Agnes-3.0-Flash-MTP-drafter/model.safetensors")
+mtp.load_weights([(k, mx.array(v)) for k, v in weights.items()])
+mtp.bind(base_model)
+```
+
+The drafter is architecture-compatible with Qwen3.5's gated attention and was extracted from the original Agnes-3.0-Flash model. See the [MTP drafter repo](https://huggingface.co/hermitdave/Agnes-3.0-Flash-MTP-drafter) for details.
+
 ## Attribution
 
 This conversion was produced by [Hermes Agent](https://hermes-agent.nousresearch.com) (Nous Research) — the autonomous research and conversion pipeline that identified the correct quantization parameters, fixed one-centered norm conversion, and validated output quality. Verified against the reference verison/Agnes-3.0-Flash-MLX-4bit model.