You can deploy this model and start earning money today!

xunkutech-ai/
Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16-mtp-draft

Name: Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16-mtp-draft
Availability: InStock

Views

No views yet

Qwythos-9B Claude Mythos 5 1M - MTP Draft Model (MLX)

This is a Qwen3.5 Multi-Token Prediction (MTP) draft model extracted from the Qwythos-9B Claude Mythos 5 1M context model, converted to MLX format for use with mlx-vlm speculative decoding.

Model Details

Property	Value
Base Model	empero-ai/Qwythos-9B-Claude-Mythos-5-1M
Source GGUF	Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf (17GB)
MLX Format	bfloat16 / float32
Architecture	Qwen3.5 MTP Draft Model
Context Length	1,048,576 tokens (1M)
Layers	32 (main) + 1 MTP layer
Hidden Size	4096
Intermediate Size	12288
Attention Heads	16
KV Heads	4
Head Dim	256
RoPE	YARN, partial_rotary_factor=0.25, factor=4.0
Block Size	3
MTP Num Hidden Layers	1
Weight Count	15 tensors
Weight Size	~464 MB

What is MTP?

Multi-Token Prediction (MTP) is a speculative decoding technique where a smaller "draft" model predicts multiple tokens ahead, which are then verified by the main model in a single pass. This can significantly speed up inference without sacrificing quality.

This draft model extracts the MTP projection weights (blk.32.nextn.*) and the MTP attention/FFN blocks from the original model, producing a standalone qwen3_5_mtp compatible drafter.

Usage

With mlx_vlm CLI

bash

mlx_vlm.generate \
  --model /path/to/Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16 \
  --draft-model /path/to/Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16-mtp-draft \
  --draft-kind mtp

With mlx_vlm Python API

python

from mlx_vlm import load_model, generate
from mlx_vlm.utils import load_prompt_cache

model = load_model("/path/to/Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16")
draft_model = load_model("/path/to/Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16-mtp-draft")

# Use draft_model with --draft-kind mtp equivalent

Weights

Key	Shape	Dtype
`fc.weight`	(4096, 8192)	bfloat16
`layers.0.input_layernorm.weight`	(4096,)	float32
`layers.0.post_attention_layernorm.weight`	(4096,)	float32
`layers.0.self_attn.q_proj.weight`	(8192, 4096)	bfloat16
`layers.0.self_attn.k_proj.weight`	(1024, 4096)	bfloat16
`layers.0.self_attn.v_proj.weight`	(1024, 4096)	bfloat16
`layers.0.self_attn.o_proj.weight`	(4096, 4096)	bfloat16
`layers.0.self_attn.q_norm.weight`	(256,)	float32
`layers.0.self_attn.k_norm.weight`	(256,)	float32
`layers.0.mlp.gate_proj.weight`	(12288, 4096)	bfloat16
`layers.0.mlp.up_proj.weight`	(12288, 4096)	bfloat16
`layers.0.mlp.down_proj.weight`	(4096, 12288)	bfloat16
`norm.weight`	(4096,)	float32
`pre_fc_norm_embedding.weight`	(4096,)	float32
`pre_fc_norm_hidden.weight`	(4096,)	float32

Extraction Process

Source GGUF (Qwythos-9B-Claude-Mythos-5-1M-MTP-BF16.gguf) parsed for MTP tensors at blk.32
15 MTP tensors extracted (BF16/FP32 only, lossless)
Keys mapped to mtp.* format for mlx-vlm splitter
Official mlx_vlm.speculative.drafters.qwen3_5_mtp.split applied to produce final drafter
Verified with strict=True load against Qwen3_5MTPDraftModel

License

Apache 2.0 (inherited from base model)

Main model: xunkutech-ai/Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16
mlx-vlm: https://github.com/ml-explore/mlx-vlm

xunkutech-ai/Qwythos-9B-Claude-Mythos-5-1M-MLX-bf16-mtp-draft