LLM EXPLORER 64,561 MODELS INDEXED

Lewi Surge Preview 3B Base by PoliteChainsaw

By PoliteChainsaw · 342 downloads
HF Repo ↗ Copy URL

Lewi Surge Preview 3B Base is an open-source language model by PoliteChainsaw. Features: 3b LLM, VRAM: 6.9GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.33.

  Base-model   Code   Conversational Dataset:bigcode/self-oss-instr... Dataset:codeparrot/github-code...   Dataset:epfml/fineweb2-hq Dataset:huggingfacefw/fineweb-... Dataset:huggingfacefw/fineweb-...   Dataset:huggingfacem4/websight   Dataset:huggingfacetb/finemath Dataset:huggingfacetb/smollm-c... Dataset:ise-uiuc/magicoder-oss... Dataset:m-a-p/codefeedback-fil... Dataset:openbmb/ultradata-sft-... Dataset:opencoder-llm/opc-anne... Dataset:opencoder-llm/opc-fine... Dataset:opencoder-llm/opc-sft-...   Dataset:starvector/svg-stack Dataset:starvector/text2svg-st...   De   En   Endpoints compatible   Es   Fr   Gated-deltanet   Instruct   Jax   Maxtext   Mixture-of-experts   Moe   Pt   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Uk
Model Card on HF 🤗: https://huggingface.co/PoliteChainsaw/Lewi-Surge-Preview-3B-Base 

Lewi Surge Preview 3B Base Parameters and Internals

LLM NameLewi Surge Preview 3B Base
Repository 🤗https://huggingface.co/PoliteChainsaw/Lewi-Surge-Preview-3B-Base 
Model Size3b
Required VRAM6.9 GB
Updated2026-10-16
MaintainerPoliteChainsaw
Model Typeqwen3_5_moe
Instruction-BasedYes
Model Files  0.3 GB   3.2 GB: 1-of-3   3.0 GB: 2-of-3   0.7 GB: 3-of-3
Supported Languagesen uk es pt fr de
Model ArchitectureQwen3_5MoeForCausalLM
Licenseapache-2.0
Model Max Length262144
Transformers Version5.17.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace