Goldkoron

Goldkoron's activity

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

New activity in Goldkoron/Qwen3.5-397B-A17B 2 months ago

Can you share KLD sensitivity data measurement scripts?

2

#4 opened 4 months ago by

cpral

New activity in Goldkoron/Qwen3.5-122B-A10B 5 months ago

Thanks! Is K_G_3.00 42.9 GiB usable in 48GB VRAM?

2

#1 opened 5 months ago by

BingoBird

New activity in Goldkoron/MiniMax-M2.7 6 months ago

K_G_3.50 quant outperforming the K_G_4.00 quant I wonder if the 4 bit didn't quantize correctly?

4

#2 opened 6 months ago by

EclipseMist

New activity in Goldkoron/Qwen3.5-397B-A17B 6 months ago

Gutenberg quants - impact on Qwen 3.5 vs Minimax 2.7?

2

#2 opened 6 months ago by

nboutaleb

New activity in Goldkoron/MiniMax-M2.7 6 months ago

The K_G_3.50 quant seems to be outperforming the UD IQ4_NL quant. Whats the difference between v1 and v2?

7

#1 opened 6 months ago by

EclipseMist

New activity in Goldkoron/Qwen3.5-397B-A17B 6 months ago

Strix Halo 1.95 BPW

4

#1 opened 6 months ago by

carrot-root

New activity in Goldkoron/Qwen3.5-397B-A17B-REAP35 6 months ago

A couple of questions

6

#1 opened 6 months ago by

jukofyork

New activity in bartowski/Qwen_Qwen3.5-397B-A17B-GGUF 7 months ago

Q3_K_XL outputs EOS token immediately, all messages result in 1 token immediate end of response

1

#3 opened 7 months ago by

Goldkoron

New activity in LatitudeGames/Hearthfire-24B 10 months ago

Awesome model

❤️ 2

2

#1 opened 10 months ago by

Goldkoron

New activity in gghfez/GLM-4.6-control-vectors 11 months ago

A description for what each one does?

1

#2 opened 11 months ago by

Goldkoron

New activity in nuigurumi/basil_mix over 3 years ago

Models used in merge

2

#11 opened over 3 years ago by

Goldkoron