Escarda 86M Base is an open-source language model by Quazim0t0. Features: 86m LLM, VRAM: 0.4GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.31.
Base-model Custom code Dataset:huggingfacefw/fineweb-... En Experimental Feature-extraction Jepa Mla Region:us Safetensors Small-models Spike whale
Model Card on HF 🤗: https://huggingface.co/Quazim0t0/Escarda-86M-Base
Escarda 86M Base Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Escarda 86M Base Parameters and Internals
| LLM Name | Escarda 86M Base |
| Repository 🤗 | https://huggingface.co/Quazim0t0/Escarda-86M-Base |
| Model Size | 86m |
| Required VRAM | 0.4 GB |
| Updated | 2026-07-30 |
| Maintainer | Quazim0t0 |
| Model Type | spike_whale |
| Model Files | |
| Supported Languages | en |
| Model Architecture | SpikeWhaleLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 5.8.0 |
| Tokenizer Class | SpikeTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 16512 |
Best Alternatives to Escarda 86M Base
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Byrne 86M | 4K / 0.4 GB | 497 | 1 |
| Escarda 86M Identity | 4K / 0.4 GB | 416 | 1 |
Rank the Escarda 86M Base Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 55501 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a