LLM EXPLORER 65,695 MODELS INDEXED

NOVA Tendo 3.8 by cortex-ai-nova

By cortex-ai-nova · 19 downloads
HF Repo ↗ Copy URL

NOVA Tendo 3.8 is an open-source language model by cortex-ai-nova. Features: 1.5b LLM, VRAM: 3.1GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.28.

  4bit Base model:finetune:unsloth/qw... Base model:unsloth/qwen2.5-cod...   Codegen   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/cortex-ai-nova/NOVA-Tendo-3.8 

NOVA Tendo 3.8 Parameters and Internals

LLM NameNOVA Tendo 3.8
Repository 🤗https://huggingface.co/cortex-ai-nova/NOVA-Tendo-3.8 
Base Model(s)  unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit   unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit
Model Size1.5b
Required VRAM3.1 GB
Updated2026-10-26
Maintainercortex-ai-nova
Model Typeqwen2
Instruction-BasedYes
Model Files  3.1 GB
Supported Languagesen
Quantization Type4bit
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version5.17.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to NOVA Tendo 3.8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 Coder 1.5B NL Java32K / 3.1 GB160
Zirel 1.532K / 3.1 GB180
Text2SQL 1.5B32K / 3.1 GB147
...5 Coder 1.5B Instruct Bnb 4bit32K / 1.1 GB139873
...en2.5 Coder 1.5B Instruct 4bit32K / 0.9 GB20302
FastApply 1.5B V1.032K / 3.1 GB91543
Merge Cord V1128K / 3.1 GB1551
Replete Coder Qwen2 1.5B128K / 3.1 GB23323
QwenDGAF Coder 1.5B32K / 1 GB5461
Temper 1 1.5B32K / 3.1 GB7160
Note: green Score (e.g. "73.2") means that the model is better than cortex-ai-nova/NOVA-Tendo-3.8.