Bonkus Cheemus

BonkusCheemus

·

BonkusCheemus

AI & ML interests

None yet

Recent Activity

repliedto IsValorum's post 13 days 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://shortbench.vercel.app/

liked a model 13 days ago

IsValorum/Huihui-Qwen3.8-27B-Coder390-EfficientThink-abliterated-VAL-APEX-I-MiniPlus-V3-GGUF

liked a model 14 days ago

ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

View all activity

Organizations

None yet

liked a model 13 days ago

IsValorum/Huihui-Qwen3.8-27B-Coder390-EfficientThink-abliterated-VAL-APEX-I-MiniPlus-V3-GGUF

Text Generation • 27B • Updated 23 days ago • 10.6k • 6

liked a model 14 days ago

ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

Text Generation • 197B • Updated 11 days ago • 3.15M • 637

liked a model 29 days ago

nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2

Image-Text-to-Text • 27B • Updated 8 days ago • 891k • 541

liked 16 models about 2 months ago

RedHatAI/Qwen3.8-27B-speculator.dspark

2B • Updated Sep 28 • 3.2k • 20

agentionai/Qwen3.8-27B-AP-GGUF

Image-Text-to-Text • 27B • Updated 11 days ago • 924k • 102

convaiinnovations/laya

Text Classification • 0.4B • Updated Oct 3 • 21.7k • • 5.93k

DeepMostInnovations/sales-conversion-model-reinf-learning

Reinforcement Learning • Updated Sep 17 • 61 • 224

1337Hero/Qwopus3.8-27B-Flash-ROCMFP4-GGUF

Image-Text-to-Text • 0.5B • Updated Sep 4 • 111 • 2

julianmb/Nex-N2.5-mini-ROCmFP4-GGUF

35B • Updated Sep 9 • 104 • 6

nex-agi/Nex-N2.5-mini

Text Generation • 35B • Updated Sep 8 • 3.09k • 880

Edge0/Edge0-35B-A3B-preview

Text Generation • 35B • Updated Oct 1 • 3.78k • 1.09k

m-a-p/YuE2-3B

Text-to-Audio • 4B • Updated Oct 6 • 23.2k • 1.24k

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF

Image-Text-to-Text • 27B • Updated Sep 17 • 40.7k • 238

jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge

Image-Text-to-Text • 27B • Updated Aug 19 • 247 • 17

jcbtc/Qwen3.8-27B-IU4-Kairic-Edge

Text Generation • 27B • Updated Sep 24 • 138 • 51

DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU

Image-Text-to-Text • 28B • Updated Sep 16 • 10.1k • • 273

DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF

Image-Text-to-Text • 27B • Updated 22 days ago • 1.55M • 2.69k

DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-ULTRA-HERETIC-Uncensored

Image-Text-to-Text • 28B • Updated Sep 19 • 716 • 78

agentionai/Signal-3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Sep 15 • 15.6k • 105

liked a model 2 months ago

DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Image-Text-to-Text • 9B • Updated 22 days ago • 2.07M • 1.48k