LLM EXPLORER 59,420 MODELS INDEXED

R4L V0.1 by Ourse

By Ourse · 7 downloads
HF Repo ↗ Copy URL

R4L V0.1 is an open-source language model by Ourse. Features: 1.5b LLM, VRAM: 3.5GB, Context: 32K, Instruction-Based, Merged, LLM Explorer Score: 0.16.

  Merged Model Base model:bunnycore/qwen2.5-1... Base model:unsloth/qwen2.5-1.5...   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Ourse/R4L-v0.1 

R4L V0.1 Parameters and Internals

LLM NameR4L V0.1
Repository 🤗https://huggingface.co/Ourse/R4L-v0.1 
Base Model(s)  bunnycore/Qwen2.5-1.5B-Matrix   unsloth/Qwen2.5-1.5B-Instruct   bunnycore/Qwen2.5-1.5B-Matrix   unsloth/Qwen2.5-1.5B-Instruct
Merged ModelYes
Model Size1.5b
Required VRAM3.5 GB
Updated2026-07-30
MaintainerOurse
Model Typeqwen2
Instruction-BasedYes
Model Files  3.5 GB: 1-of-1
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.46.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to R4L V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 1.5B 1.3M Stretched1280K / 3.1 GB110
Merge Cord V1128K / 3.1 GB1551
Gte Qwen2 1.5B Instruct128K / 7.1 GB899648237
AceInstruct 1.5B128K / 3.5 GB13922
... Abliterated TIES Qwen2.5 1.5B128K / 3.5 GB150
Saba1 1.8B128K / 3.6 GB61
Miniclaus Qw1.5B UNAMGS128K / 3.5 GB128
Bellatrix 1.5B XElite128K / 3.5 GB193
GCIRS Reasoning 1.5B R1128K / 3.5 GB91
...illed Scout 1.5B Instruct Gen1128K / 3.5 GB100
Note: green Score (e.g. "73.2") means that the model is better than Ourse/R4L-v0.1.