Downloads · 30 days
1.1K
4% of all-time downloads
stamsam/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-MLX-oQ4-MTP
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-MLX-oQ4-MTP is a text generation model from stamsam. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
MLX/oMLX 4-bit conversion of r3lax/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled with Qwen MTP tensors preserved and runtime-tested in oMLX.
Downloads · 30 days
1.1K
4% of all-time downloads
All-time downloads
29.9K
Public
Parameters
34.7B
20 GB on disk
Likes
30
Public
Click a slice to open those files.
.safetensors20 GB · 100%
How the weights are stored.
U3235.5B · 100%
From the Hugging Face model README
MLX/oMLX 4-bit conversion of
r3lax/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled
with Qwen MTP tensors preserved and runtime-tested in oMLX.
This is not a new training run or fine-tune. Weights were only converted/quantized for local MLX/oMLX inference.
MTP config: mtp_num_hidden_layers=1, mtp_use_dedicated_embeddings=false
MTP tensor entries: 42
MTP fusion projection: language_model.mtp.fc.weight present and full precision
Runtime: oMLX logged native MTP path activation during smoke tests
MTP support is runtime-specific. These tensors are preserved, but non-oMLX runtimes may ignore them.
Measured on an M5 Pro Mac with 48GB unified memory using oMLX.
MTP on average: ~89.9 tok/s
MTP off average: ~86.0 tok/s
Speed lift: ~+4.6% with native MTP enabled
Per-prompt MTP-on smoke results:
count120: 160 tokens, 1.726s, 92.69 tok/s, MTP accept 79/79 and 79/79
rain180: 220 tokens, 2.465s, 89.26 tok/s, MTP accept 96/123 and 98/121
jsoncities: 128 tokens, 1.457s, 87.86 tok/s, MTP accept 64/65 and 64/64
These are local smoke numbers, not a universal benchmark. Prompt, cache state, batching, oMLX version, and hardware will change results.
Place the model under your oMLX model directory and enable native MTP:
~/.omlx/models/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-MLX-oQ4-MTP
Recommended oMLX settings:
{
"mtp_enabled": true,
"dflash_enabled": false,
"turboquant_kv_enabled": false
}
Credit to the upstream work:
Qwen/Qwen3.6-35B-A3B for the base model.lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled for the Claude Opus 4.7 reasoning distillation.r3lax/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled for the source checkpoint used here.Please credit the upstream authors if you use or redistribute this conversion.
<think> traces; set max_tokens intentionally.Apache-2.0, following the upstream model metadata. Check upstream model cards and any teacher-data usage policies before redistribution or commercial deployment.