LLM EXPLORER 59,420 MODELS INDEXED

QuadConnect2.5 0.5B V0.0.9B by Lyte

By Lyte · 47 downloads
HF Repo ↗ Copy URL

QuadConnect2.5 0.5B V0.0.9B is an open-source language model by Lyte. Features: 0.5b LLM, VRAM: 0.5GB, Context: 32K, Quantized, Instruction-Based, LLM Explorer Score: 0.17.

  Arxiv:2402.03300   4bit   Connect4   Conversational   Dataset:lyte/connectfour-t10   En   Endpoints compatible   Gguf   Grpo   Instruct   Quantized   Qwen   Qwen2   Region:us   Rl   Safetensors   Tensorboard   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Lyte/QuadConnect2.5-0.5B-v0.0.9b 

QuadConnect2.5 0.5B V0.0.9B Parameters and Internals

LLM NameQuadConnect2.5 0.5B V0.0.9B
Repository 🤗https://huggingface.co/Lyte/QuadConnect2.5-0.5B-v0.0.9b 
Model NameQuadConnect2.5-0.5B-v0.0.9b
Base Model(s)  unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit   unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
Model Size0.5b
Required VRAM0.5 GB
Updated2026-08-06
MaintainerLyte
Model Typeqwen2
Instruction-BasedYes
Model Files  1.0 GB   0.0 GB   0.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|4bit
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.49.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to QuadConnect2.5 0.5B V0.0.9B

Best Alternatives
Context / RAM
Downloads
Likes
Soulbox Cbt Therapy 0.5B32K / 0.4 GB810
Flowscribe Qwen2.5 0.5B V232K / 0.4 GB490
Qwen2.5 Coder 0.5B Merged32K / 1.3 GB290
Qwen2 0.5B Instruct GGUF32K / 0.3 GB2120
Qwen2 0.5B Instruct GGUF32K / 0.3 GB1061
Pgabl Ft Nama Siswa32K / 1 GB2530
Legal Rag Qwen Sft32K / 1 GB2040
Atomight V2.2 UltraThink 0.5B32K / 1 GB541
...mmanuel Siagian Exp1 Lr2e5 R1632K / 1 GB110
BoyBarley Sparky32K / 1 GB170
Note: green Score (e.g. "73.2") means that the model is better than Lyte/QuadConnect2.5-0.5B-v0.0.9b.