David Belton

DavidAU's activity

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

New activity in sam-paech/Qwen3-4B-antislop-exp15 about 16 hours ago

Heads up ; used this in a series of merges / random pruning 8 models.

3

#1 opened about 16 hours ago by

DavidAU

New activity in mradermacher/model_requests about 16 hours ago

Request - 17 Qwen 3 4B models quanted?

3

#1014 opened about 17 hours ago by

DavidAU

New activity in mradermacher/model_requests 1 day ago

Ah... went a little overboard... 12 new models. // err.. 13...

5

#1005 opened 3 days ago by

DavidAU

New activity in DavidAU/L3-Dark-Planet-8B-wordstorm-b6 2 days ago

When could we have "Qwen3-14B-192k-Josiefied-Uncensored-NEO-Max-GGUF"?

4

#1 opened 3 days ago by

Tonight223

New activity in DavidAU/Qwen3-30B-A6B-16-Extreme-128k-context 2 days ago

Draft 0.6B model to pair it with in LMStudio?

2

#2 opened 2 days ago by

ljupco

New activity in DavidAU/Qwen3-8B-192k-Josiefied-Uncensored-NEO-Max-GGUF 11 days ago

LM Studio

1

#4 opened 11 days ago by

XiozTzu1000

New activity in DavidAU/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-GGUF 12 days ago

Query Regarding "num_experts_used" and "repetition_penalty" for L3.2 MOE GGUF Model with Ollama

3

#4 opened 13 days ago by

Soloolos

New activity in DavidAU/Qwen3-8B-192k-Josiefied-Uncensored-NEO-Max-GGUF 13 days ago

josiefied 4b

👍 1

2

#3 opened 15 days ago by

spinochenza

New activity in DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF 16 days ago

Context size 4096 tokens?

1

#2 opened 16 days ago by

Pentium95

New activity in DavidAU/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B 16 days ago

Love these models

🔥 1

1

#1 opened 16 days ago by

SuperbEmphasis

New activity in DavidAU/Llama-3.2-8X3B-GATED-MOE-Horror-Reasoning-Dark-Champion-uncensored-18.4B-IMAT-GGUF 16 days ago

Base version

1

#1 opened 16 days ago by

lazyDataScientist

New activity in DavidAU/Qwen3-8B-192k-Josiefied-Uncensored-NEO-Max-GGUF 17 days ago

When can we have Josiefied for Qwen3-32B 128k uncensored?

👍 1

2

#2 opened 18 days ago by

Tonight223

New activity in DavidAU/How-To-Set-and-Manage-MOE-Mix-of-Experts-Model-Activation-of-Experts 17 days ago

fix llama-server doc url

🔥 2

#1 opened 23 days ago by

wbruna

New activity in DavidAU/Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF 18 days ago

Request

👍 2

2

#2 opened 18 days ago by

FrescoHF

New activity in DavidAU/Reka-Flash-3-21B-Reasoning-Uncensored-MAX-NEO-Imatrix-GGUF 18 days ago

Instruct Template?

6

#2 opened 3 months ago by

Varkoyote

New activity in Gryphe/Pantheon-Proto-RP-1.8-30B-A3B 18 days ago

Feedback after some use

❤️ 👍 3

5

#1 opened 26 days ago by

AlecFoster

New activity in DavidAU/L3-Stheno-v3.2-12.2B-INSTRUCT-ULTRA-F32-GGUF 19 days ago

Can you add an IQ3_XS version?

1

#1 opened 20 days ago by

flesler

New activity in mradermacher/model_requests 20 days ago

Gated Moe Model + How to "Imatrix" Qwen 3's 30B-A3Bs ;

8

#939 opened 21 days ago by

DavidAU

New activity in DavidAU/Qwen3-30B-A6B-16-Extreme 20 days ago

GPTQ/AWQ quants

1

#3 opened 21 days ago by

tensornet

New activity in DavidAU/Qwen3-30B-A6B-16-Extreme-128k-context 21 days ago

Jinja template error in LMStudio

2

#1 opened 21 days ago by

ljupco