Nick M

veldierin's activity

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

New activity in EryriLabs/Caelum-G4-38B-A12.5B about 8 hours ago

traditional gemma-4-12b draft mtp head (assistant) capable, and thoughts about QAT version as well?

#1 opened about 8 hours ago by

veldierin

New activity in DavidAU/Llama-3.2-4X3B-MOE-Hell-California-Uncensored-10B-GGUF 1 day ago

Question about chat template

3

#7 opened 1 day ago by

brewbadgertim

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

Hermes Agent + chat template: tool calls fail silently (XML vs JSON format)

👍❤️ 7

3

#46 opened 19 days ago by

k-mktr

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-ReducedRefusal-MTPLX-6bit 7 days ago

Would it be worthwhile to provide links in the README.md to some of the source discussions/models?

3

#1 opened 8 days ago by

veldierin

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP 11 days ago

Issues with Using Models in OpenCode

4

#4 opened 11 days ago by

warlock-edward

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-6bit 12 days ago

You posted some raw TG numbers with/without MTP - do you happen to have TG/PP at higher contexts?

7

#1 opened 14 days ago by

veldierin

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 12 days ago

Absolute Beast : Claude (Opus) Level of performance confirmed

👀❤️ 20

15

#41 opened 13 days ago by

tcclaviger

Abliteration not working

👍 2

57

#13 opened 19 days ago by

Dhrhciebcy

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 14 days ago

Love the prose it writes, but it constantly (AMD) splits 60% to the CPU, 20-30% to my GPU

👍 1

18

#33 opened 15 days ago by

rboluyt

New activity in nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-Tess-1M-qx64-hi-mlx 20 days ago

Can we expect the Qwen3.6-35B MOE version of this?

❤️ 1

13

#1 opened 20 days ago by

cnsiva

New activity in DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 20 days ago

Plans for BF16 to allow for MLX quantizations?

2

#1 opened 20 days ago by

veldierin

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 20 days ago

It it not a thinking model?

3

#7 opened 20 days ago by

nickmok

New activity in froggeric/Qwen-Fixed-Chat-Templates 25 days ago

Odd issues with v21.3 with tool calling that didn't happen with previous version

➕ 2

#64 opened 25 days ago by

veldierin

New activity in DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF about 1 month ago

Any possibility to apply this distillation/finetune to qwen3.6-35b-a3b ?

1

#14 opened about 1 month ago by

veldierin

New activity in froggeric/Qwen-Fixed-Chat-Templates about 1 month ago

[feat request] llama.cpp --reasoning-preserve

2

#54 opened about 1 month ago by

crusaderky

chat template v21.3

🔥 7

12

#51 opened about 1 month ago by

froggeric

Non-thinking generation prompt uses non-canonical `<think>\n</think>\n` → duplicated output under streaming

6

#43 opened about 2 months ago by

batsclamp

New activity in llmfan46/Nex-N2-mini-ultra-uncensored-heretic-GGUF about 2 months ago

llama.cpp cannot load that GGUF because an expected tensor is missing, model Nex-N2-mini-ultra-uncensored-heretic-BF16.gguf

12

#1 opened about 2 months ago by

SetiAtHome

New activity in DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF about 2 months ago

I am getting very good results with this model but its a bit slow, any chance for MTP?

33

#17 opened about 2 months ago by

bissli

New activity in mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF 2 months ago

reasoning loop

11

#2 opened 2 months ago by

lobstertot