Kir Belevich

deepsweet's activity

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

New activity in deepsweet/Qwen3.6-27B-DFlash-FP16 24 days ago

How can I convert z-lab/Qwen3.8-27B-DFlash2 to fp16?

2

#2 opened 26 days ago by

crazyi

Openclaw compatibility problem

1

#1 opened 5 months ago by

felkf

New activity in ornith-ai/Ornith-1.0-35B 3 months ago

Two critical checkpoint errors prevent quantization (MTP config mismatch + wrong tensor naming)

🔥 2

2

#15 opened 3 months ago by

Maennekes

New activity in deepsweet/Qwen3.6-27B-MLX-VL-oQ6 4 months ago

Version that preserves MTP Heads

❤️ 1

2

#3 opened 4 months ago by

david-king-neuma

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

[bot] Conversion to Parquet

#1 opened 4 months ago by

parquet-converter

New activity in deepsweet/Qwen3.6-27B-MLX-VL-oQ6 4 months ago

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

❤️ 1

3

#2 opened 4 months ago by

evkt

New activity in deepsweet/Qwen3.6-27B-MLX-oQ8-FP16 4 months ago

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

👀 1

1

#4 opened 4 months ago by

adampotocki

New activity in deepsweet/Qwen3.6-27B-MLX-VL-oQ6 4 months ago

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

❤️ 1

1

#1 opened 4 months ago by

nreliu

New activity in deepsweet/Qwen3.6-27B-MLX-oQ8-FP16 4 months ago

Is there a benchmark comparison between DFLASH and native MTP?

3

#3 opened 4 months ago by

crazyi

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

1

#2 opened 4 months ago by

alexaione

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8 4 months ago

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

4

#1 opened 4 months ago by

alexaione

New activity in unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit 5 months ago

There is no benchmark for mlx models

👍 1

7

#4 opened 5 months ago by

zaskara

New activity in deepsweet/Qwen3.6-27B-MLX-oQ8-FP16 5 months ago

The original Qwen3.6-27B is multimodal

8

#1 opened 5 months ago by

crazyi

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ4 5 months ago

Some questions

2

#2 opened 5 months ago by

FaheemIqbal

New activity in z-lab/Qwen3.6-27B-DFlash 5 months ago

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

3

#4 opened 5 months ago by

BeCreated

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-VL-oQ8-FP16 5 months ago

non FP16 : M3+ version of VLM

2

#2 opened 5 months ago by

jeromelaurens

M1 Ultra 64GB FP16 improvements

9

#1 opened 5 months ago by

KnucklesXBT

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16 5 months ago

Can we support image to text in this model?

3

#2 opened 5 months ago by

mastervivi

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ4 5 months ago

🛠️ revert chat template to the original one

#1 opened 5 months ago by

deepsweet

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16 5 months ago

🛠️ revert chat template to the original one

#1 opened 5 months ago by

deepsweet