LLM EXPLORER 61,060 MODELS INDEXED

MAXWELL by Xerv-AI

By Xerv-AI · 115 downloads
HF Repo ↗ Copy URL

MAXWELL is an open-source language model by Xerv-AI. Features: 1.5b LLM, VRAM: 3.1GB, Context: 4K, License: apache-2.0, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.24.

  Merged Model   4bit   Analytical Base model:finetune:unsloth/qw... Base model:unsloth/qwen2.5-mat...   Conversational   Dataset:xerv-ai/tart   En   Endpoints compatible   Eval-results   Fp16   Instruct   Logic   Mathematics   Meta-aggregation   Model-index   Physics   Quantized   Qwen2   Qwen2.5-math   Reasoning   Region:us   Safetensors   Science   Stem   Stss-framework   Unsloth
Model Card on HF 🤗: https://huggingface.co/Xerv-AI/MAXWELL 

MAXWELL Parameters and Internals

LLM NameMAXWELL
Repository 🤗https://huggingface.co/Xerv-AI/MAXWELL 
Model NameMAXWELL
Model CreatorXerv-AI
Base Model(s)  unsloth/Qwen2.5-Math-1.5B-Instruct-bnb-4bit   unsloth/Qwen2.5-Math-1.5B-Instruct-bnb-4bit
Merged ModelYes
Model Size1.5b
Required VRAM3.1 GB
Updated2026-06-30
MaintainerXerv-AI
Model Typeqwen2
Instruction-BasedYes
Model Files  3.1 GB
Supported Languagesen
Quantization Typefp16|4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to MAXWELL

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 1.5B Instruct Legal Id32K / 3.1 GB14250
Legal Chatbot Llama3 Finetuned32K / 3.1 GB2970
Legal Chatbot Llama3 Finetuned32K / 3.1 GB3890
Legal Qwen2.5 1.5B Sft32K / 3.1 GB10310
Legal Chatbot Qwen2.5 1.5B Sft32K / 3.1 GB8710
....5B Instruct Legal Chatbot Sft32K / 3.1 GB5920
Qwen2.5 1.5B Legal Sft32K / 3.1 GB6770
Legal Chatbot Qwen2.5 1.5B Sft32K / 3.1 GB5060
... 2.5 1.5B Indonesian Legal Sft32K / 3.1 GB4540
...wen2.5 1.5B Legal Id Finetuned32K / 3.1 GB3450
Note: green Score (e.g. "73.2") means that the model is better than Xerv-AI/MAXWELL.