LLM EXPLORER 66,291 MODELS INDEXED

Apex 3 by YOON1v

By YOON1v · 57 downloads

Apex 3 is an open-source language model by YOON1v. Features: 21b LLM, VRAM: 42.2GB, Context: 8K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.32.

  Apex3   Chat   Code   Conversational   Custom code Dataset:agentica-org/deepcoder... Dataset:agentica-org/deepscale... Dataset:allenai/dolci-think-dp... Dataset:allenai/dolci-think-rl... Dataset:allenai/dolmino-mix-11...   Dataset:allenai/pes2o Dataset:allenai/rlvr-gsm-math-... Dataset:bigcode/starcoder2data...   Dataset:bigcode/starcoderdata Dataset:bigcode/the-stack-v2-d...   Dataset:emozilla/pg19   Dataset:gair/limo Dataset:huggingfacefw/finepdfs... Dataset:huggingfacefw/fineweb-...   Dataset:huggingfacetb/finemath Dataset:huggingfacetb/smollm-c... Dataset:huggingfacetb/stack-ed...   Dataset:likaixin/taco-verified   Dataset:llm360/megamath Dataset:mlfoundations/dclm-bas... Dataset:nvidia/acereason-1.1-s... Dataset:nvidia/nemotron-rl-ins... Dataset:nvidia/opencodereasoni... Dataset:nvidia/openmathreasoni... Dataset:nvidia/opensciencereas... Dataset:open-r1/openr1-math-22... Dataset:open-thoughts/openthou... Dataset:open-web-math/open-web...   Dataset:openassistant/oasst2 Dataset:primeintellect/synthet... Dataset:tokyotech-llm/swallow-... Dataset:tokyotech-llm/swallow-...   Dataset:wikimedia/wikipedia   Diloco   Dpo   En   From-scratch   Gh200   Grpo   Instruct   Llm-from-scratch   Math   Mixture-of-experts   Model-index   Moe   Muon   No-think   Region:us   Rlvr   Safetensors   Sharded   Superbpe   Tensorflow
Model Card on HF πŸ€—: https://huggingface.co/YOON1v/Apex-3 

Apex 3 Parameters and Internals

LLM NameApex 3
Repository πŸ€—https://huggingface.co/YOON1v/Apex-3 
Model Size21b
Required VRAM42.2 GB
Updated2026-10-31
MaintainerYOON1v
Model Typeapex3
Instruction-BasedYes
Model Files  1.7 GB: 1-of-23   1.8 GB: 2-of-23   1.9 GB: 3-of-23   1.8 GB: 4-of-23   1.8 GB: 5-of-23   1.9 GB: 6-of-23   1.8 GB: 7-of-23   1.8 GB: 8-of-23   1.9 GB: 9-of-23   1.8 GB: 10-of-23   1.8 GB: 11-of-23   1.9 GB: 12-of-23   1.8 GB: 13-of-23   1.8 GB: 14-of-23   1.9 GB: 15-of-23   1.8 GB: 16-of-23   1.8 GB: 17-of-23   1.9 GB: 18-of-23   1.8 GB: 19-of-23   1.8 GB: 20-of-23   1.9 GB: 21-of-23   1.8 GB: 22-of-23   2.0 GB: 23-of-23
Supported Languagesen
Model ArchitectureApex3ForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size204800
Torch Data Typebfloat16