Edmund Tan

crystech's activity

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

New activity in deepseek-ai/DeepSeek-V4.1-Flash-1017 3 days ago

DeepSeek V4.1 Flash 1017 Successfully on 3 X RTX Pro 6000D 84GB + 1 x RTX Pro 6000 Workstation Edition 96GB (Huge saving using 6000D)

1

#79 opened 3 days ago by

crystech

New activity in unsloth/Qwen3.8-27B-NVFP4 3 months ago

Using this on vllm but excessive tbinking

👀➕ 3

8

#13 opened 3 months ago by

crystech

New activity in mlx-community/GLM-5.2-4bit 5 months ago

big thank you for providing this 4bit mlx.

🚀 1

1

#1 opened 5 months ago by

crystech

New activity in MiniMaxAI/MiniMax-M2.7 5 months ago

minimax 3 什么时候开源？

25

#33 opened 6 months ago by

wpfnnnns

New activity in zai-org/GLM-4.6V-FP8 7 months ago

tokenizer issues when loading model in vllm

3

#3 opened 11 months ago by

crystech

New activity in Qwen/Qwen3.5-397B-A17B 9 months ago

any AWQ quantized model ??

3

#29 opened 9 months ago by

crystech

fake knowledge 假知识

6

#21 opened 9 months ago by

aabbccddwasd

New activity in QuantTrio/GLM-4.7-AWQ 10 months ago

Once again Thanks, here is my review for 8 x RTX 5090 setup

17

#2 opened 11 months ago by

crystech

liked a model 11 months ago

QuantTrio/GLM-4.7-AWQ

Text Generation • 358B • Updated May 18 • 389 • 28

New activity in QuantTrio/GLM-4.6-AWQ 11 months ago

This model is awesome!

👀🚀 2

3

#4 opened 11 months ago by

crystech

New activity in Salyut1/GLM-4.7-NVFP4 11 months ago

Trying out later with 8 x RTX 5090

2

#1 opened 11 months ago by

crystech

New activity in RESMP-DEV/GLM-4.6-NVFP4 11 months ago

rtx

14

#1 opened about 1 year ago by

festr2

New activity in Qwen/Qwen3-VL-235B-A22B-Thinking 11 months ago

How much vram is needed to run this model? 8xRTX3090=192GB isn't enough to run the context.

1

#12 opened about 1 year ago by

kq

New activity in cyankiwi/GLM-4.6V-AWQ-8bit 11 months ago

Tool calling in cline failed after few iterations

#2 opened 11 months ago by

crystech

New activity in QuantTrio/Qwen3-Coder-480B-A35B-Instruct-AWQ 11 months ago

How to use CPU Offload for this model? I keep getting OOM

1

#4 opened 11 months ago by

crystech

liked a model 12 months ago

lukealonso/GLM-4.6-NVFP4

177B • Updated Nov 3, 2025 • 139 • 6

New activity in zai-org/GLM-4.6 about 1 year ago

Will release Air version of GLM-4.6?

➕ 12

3

#9 opened about 1 year ago by

rosspanda0

New activity in QuantTrio/Qwen3-VL-235B-A22B-Instruct-AWQ about 1 year ago

Output on 2nd Request

4

#1 opened about 1 year ago by

ryanstout