Steve Li

CHNtentes's activity

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

New activity in pastapaul/DeepSeek-V4-Flash-W4A16-FP8 about 19 hours ago

Can I run this model on 2x H20 141GB?

3

#1 opened 1 day ago by

CHNtentes

New activity in havenoammo/Qwen3.6-35B-A3B-MTP-GGUF about 22 hours ago

Is it possible to only download the mtp gguf (<1GB one) to use with existing ggufs?

2

#3 opened 1 day ago by

CHNtentes

New activity in appmana/deepseek-v4-int8-int4-sglang 1 day ago

Is it possible to use this model on hopper cards?

#1 opened 1 day ago by

CHNtentes

New activity in deepseek-ai/DeepSeek-V4-Pro 3 days ago

Will there be small models like 12b?

👍👀 4

14

#164 opened 8 days ago by

Crownelius

New activity in deepseek-ai/DeepSeek-V4-Flash 10 days ago

Too big to run locally.

🤯👍 9

19

#12 opened 15 days ago by

Dampfinchen

New activity in deepseek-ai/DeepSeek-V4-Pro 15 days ago

所以我猜是混合精度加模型太大导致暂时还没有量化的模型出来

6

#96 opened 15 days ago by

lzm1066258

New activity in deepseek-ai/DeepSeek-V4-Flash 15 days ago

May I ask if there is a deployment document?

2

#10 opened 15 days ago by

jerryliujiawei

New activity in Qwen/Qwen3.6-27B-FP8 16 days ago

Parameter model.layers.15.mlp.gate_gate_up_proj.weight_scale_inv not found in params_dict

5

#3 opened 16 days ago by

CHNtentes

New activity in Qwen/Qwen3.6-35B-A3B 17 days ago

太吃显存啦

6

#21 opened 22 days ago by

yukojiangjiang

New activity in cyankiwi/MiniMax-M2.7-AWQ-4bit 24 days ago

These are NOT actual AWQ-quantized models.

4

#2 opened 24 days ago by

cai-cai

New activity in unsloth/MiniMax-M2.7-GGUF 26 days ago

larger file size for same quant

5

#4 opened 27 days ago by

CHNtentes

New activity in Tongyi-MAI/MAI-UI-8B 27 days ago

will we ever get 32b and 235b versions?

#4 opened 27 days ago by

CHNtentes

New activity in zai-org/GLM-5.1 28 days ago

GLM5.1角色问题-重要

9

#17 opened 29 days ago by

liuyt6515

New activity in MiniMaxAI/MiniMax-M2.5 about 2 months ago

can we get minimax-m2.7

🤗 13

5

#49 opened about 2 months ago by

CHNtentes

New activity in Tesslate/OmniCoder-9B about 2 months ago

35b variant?

👍 4

9

#2 opened about 2 months ago by

dagbs

New activity in Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled about 2 months ago

FP8 Version for running on vLLM with hardware optimizations from Ada+ generation GPUs

4

#14 opened about 2 months ago by

AQLabs

New activity in Qwen/Qwen3.5-0.8B 2 months ago

Could someone make Qwen/Qwen3.5-0.4B?

3

#4 opened 2 months ago by

MihaiPopa-1

New activity in Qwen/Qwen3.5-9B 2 months ago

Can we get a 9B-FP8 version next

👍 15

5

#5 opened 2 months ago by

kq

New activity in unsloth/Qwen3.5-9B-GGUF 2 months ago

Massive clipping damage? Why is Q8KXL have F16 tensors/layers when it's a native BF16 model?

👍 1

8

#3 opened 2 months ago by

RyanoSaurus-Wrex

New activity in Qwen/Qwen3.5-35B-A3B 2 months ago

Is `qwen3_nonthinking.jinja` available for disabling thinking?

7

#23 opened 2 months ago by

kraftDong