Kir Belevich

deepsweet's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in deepsweet/Qwen3.6-27B-MLX-VL-oQ6 about 23 hours ago

Version that preserves MTP Heads

❤️ 1

1

#3 opened 1 day ago by

david-king-neuma

New activity in deepsweet/MLX-oQ-sensitivity-map 4 days ago

[bot] Conversion to Parquet

#1 opened 7 days ago by

parquet-converter

New activity in deepsweet/Qwen3.6-27B-MLX-VL-oQ6 14 days ago

Any chance to get deepsweet/Qwen3.6-27B-MLX-oQ6 :)

❤️ 1

3

#2 opened 14 days ago by

evkt

New activity in deepsweet/Qwen3.6-27B-MLX-oQ8-FP16 16 days ago

Please upload a Qwen3.6-27B-MLX-VL-oQ8 for M3+

👀 1

1

#4 opened 17 days ago by

adampotocki

New activity in deepsweet/Qwen3.6-27B-MLX-VL-oQ6 18 days ago

404 error at https://huggingface.co/deepsweet/Qwen3.6-27B-MLX-VL-oQ6-FP16

❤️ 1

1

#1 opened 19 days ago by

nreliu

New activity in deepsweet/Qwen3.6-27B-MLX-oQ8-FP16 20 days ago

Is there a benchmark comparison between DFLASH and native MTP?

3

#3 opened 20 days ago by

crazyi

Please upload a Qwen3.6-27B-MLX-VL-oQ6 for M3

1

#2 opened 21 days ago by

alexaione

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8 21 days ago

Please build a Qwen3.6-35B-A3B-MLX-VL-oQ6

4

#1 opened 22 days ago by

alexaione

New activity in unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit 24 days ago

There is no benchmark for mlx models

👍 1

7

#4 opened 29 days ago by

zaskara

New activity in deepsweet/Qwen3.6-27B-MLX-oQ8-FP16 25 days ago

The original Qwen3.6-27B is multimodal

8

#1 opened 29 days ago by

crazyi

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ4 25 days ago

Some questions

2

#2 opened 28 days ago by

FaheemIqbal

New activity in deepsweet/Qwen3.6-27B-DFlash-FP16 27 days ago

Openclaw compatibility problem

1

#1 opened 28 days ago by

felkf

New activity in z-lab/Qwen3.6-27B-DFlash 27 days ago

I used it on Omlx,but it showed thinking as content.

3

#4 opened about 1 month ago by

BeCreated

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8-FP16 about 1 month ago

non FP16 : M3+ version of VLM

2

#2 opened about 1 month ago by

jeromelaurens

M1 Ultra 64GB FP16 improvements

9

#1 opened about 1 month ago by

KnucklesXBT

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16 about 1 month ago

Can we support image to text in this model?

3

#2 opened about 1 month ago by

mastervivi

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ4 about 1 month ago

🛠️ revert chat template to the original one

#1 opened about 1 month ago by

deepsweet

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16 about 1 month ago

🛠️ revert chat template to the original one

#1 opened about 1 month ago by

deepsweet

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ8 about 1 month ago

🛠️ revert chat template to the original one

#1 opened about 1 month ago by

deepsweet

New activity in Qwen/Qwen3.6-35B-A3B about 1 month ago

Add LICENSE file

👍 1

#33 opened about 1 month ago by

deepsweet