jaithree PRO

jaithree

·

https://huggingface.co/jaithree

AI & ML interests

Language, lingo, jargon, parlance...

Recent Activity

reacted to IsValorum's post with 🔥 about 14 hours ago

Navigating the APEX-I and VAL-APEX Quantization Ecosystem on Hugging Face As the catalog approaches 400,000 total downloads across 69 releases, all models are now structured into dedicated official collections on Hugging Face. Our goal remains consistent: eliminate the compromise between memory overflow and cognitive collapse on consumer hardware (especially 16 GB VRAM GPUs like the RTX 4080, RTX 4070 Ti Super, and RX 7800 XT). Instead of uniform block quantization, all APEX builds use per-tensor mixed precision guided by 4-moment Importance Matrix statistics: - MiniPlus Tier (approx. 14 to 14.8 GiB): Strict 0% 2-bit policy. All MoE routed experts locked at minimum IQ3_XXS with Q4_K/Q6_K attention. Designed for 24 GB setups or 16 GB setups with moderate context. - NanoPlus Tier (approx. 11.5 to 12.3 GiB): Strategic use of IQ2_S/IQ2_XXS exclusively in core feedforward blocks, keeping routers and attention high-precision. Leaves ample VRAM for 16k-32k context on 16 GB GPUs. Explore the active collections: - MoE Standard (MiniPlus & NanoPlus): https://huggingface.co/collections/IsValorum/apex-i-miniplus-v21-standard-moe-6acfee77961c8c0cf5a083b5 - MoE Abliterated (MiniPlus & NanoPlus): https://huggingface.co/collections/IsValorum/apex-i-miniplus-v21-abliterated-moe-6acfee762fc4a8cf2298c55b - 27B Dense Hybrids: https://huggingface.co/collections/IsValorum/val-apex-miniplus-standard-27b-6acfec54ca4ce4cf5cd5bdb6 - Apple Silicon (MLX): https://huggingface.co/collections/IsValorum/mlx-apex-abliterated-6abedb1f9d400e984efe4fc6 Full technical article and sizing breakdown: https://huggingface.co/blog/IsValorum

liked a model 4 days ago

ReadyArt/Wicked-Tutu-26B-A4B-v0.26

liked a model 4 days ago

ReadyArt/Wicked-Tutu-31B-v4

View all activity

Organizations

New activity in inflatebot/MN-12B-Mag-Mell-R1 11 days ago

Permission to use Mag Mell in a free game (donations + Patreon early access)

#21 opened 12 days ago by

New activity in nightmedia/gemma-4-E4B-Holodeck about 2 months ago

Thanks for this

#1 opened about 2 months ago by

New activity in Nimbz/Schattenblume-31B 2 months ago

Thanks!

#1 opened 2 months ago by

New activity in ReadyArt/gemma-4-31B-it-scotoma-2 2 months ago

Will we ever get a 12b or 26b version for those of us with 12-16gb vram?

#2 opened 3 months ago by

DontPutFishInIt

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 2 months ago

Club 0.720: models based on Fable-Fusion-711

#76 opened 2 months ago by

New activity in DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF 3 months ago

Stronger De-censored Version - DARK ROAST.

#16 opened 3 months ago by

New activity in DragonBophades/Elster-Qwen3.6-27B 3 months ago

She looks extremely pleased :)

#2 opened 3 months ago by

New activity in nightmedia/Qwen3.6-27B-Yangtze-mxfp4-mlx 3 months ago

Alchemists of the manifold

#1 opened 3 months ago by

New activity in ReadyArt/Serenity-31B-v1.1 3 months ago

Thank you for the safetensors

#1 opened 3 months ago by

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 3 months ago

VERSION: MLX --- Can we also get oMLX version? with MTP support plz

#37 opened 3 months ago by

New activity in ReadyArt/Dark-Scarlett-v1.0-26B-A4B-GGUF 4 months ago

My Feedback

#1 opened 4 months ago by

New activity in ReadyArt/Serenity-31B 4 months ago

Wtf did you cook?

#1 opened 4 months ago by