LLM EXPLORER 68,292 MODELS INDEXED

Opusculum 1.5B by Stoned-Code

By Stoned-Code · 55 downloads

Opusculum 1.5B is an open-source language model by Stoned-Code. Features: 1.5b LLM, Context: 32K, License: apache-2.0, Quantized, Instruction-Based.

  4bit Base model:finetune:unsloth/qw... Base model:unsloth/qwen2.5-1.5...   Conversational Dataset:anthracite-org/kalo-op... Dataset:anthracite-org/kalo mi... Dataset:anthracite-org/kalo op... Dataset:anthracite-org/nopm cl... Dataset:delta-vector/hydrus-cl... Dataset:epiculous/synthrp-gens... Dataset:epiculous/synthstruct-... Dataset:lodrick-the-lafted/kal...   Dataset:stoned-code/magnum-v4   En   Instruct   Quantized   Qwen2   Region:us   Safetensors   Unsloth

Opusculum 1.5B Parameters and Internals

LLM NameOpusculum 1.5B
Repository πŸ€—https://huggingface.co/Stoned-Code/Opusculum-1.5B 
Model Nameunsloth/Qwen2.5-1.5B
Base Model(s)  unsloth/Qwen2.5-1.5B-bnb-4bit   unsloth/Qwen2.5-1.5B-bnb-4bit
Model Size1.5b
Required VRAM0 GB
Updated2026-11-22
MaintainerStoned-Code
Model Typeqwen2
Instruction-BasedYes
Model Files  3.1 GB   4.5 GB   0.0 GB   0.0 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version5.5.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936

Best Alternatives to Opusculum 1.5B

Best Alternatives
Context / RAM
Downloads
Likes
Novius Qlux32K / 3.1 GB861
Qwen25 1.5B Alpaca Id Sft32K / 3.1 GB20380
Quantrexa Prime 1.5B32K / 3.1 GB4971
Qwen2.5 1.5B Instruct Legal Id32K / 3.1 GB14250
....5 1.5B Instruct Alpaca Id Sft32K / 3.1 GB3320
Qwen2.5 1.5B Legal Sft32K / 3.1 GB490
Vera Qwen 1.5B DPO32K / 3.1 GB3811
Legal Chatbot Finetuned32K / 3.1 GB3410
Legal Assistant Sft32K / 3.1 GB3121
Legal Chatbot Llama3 Finetuned32K / 3.1 GB3890
Note: green Score (e.g. "73.2") means that the model is better than Stoned-Code/Opusculum-1.5B.