LLM EXPLORER 56,604 MODELS INDEXED

Gemma 4 31B Glimmer Rp V0.2 by BirdToast

By BirdToast · 19 downloads
HF Repo ↗ Copy URL

Gemma 4 31B Glimmer Rp V0.2 is an open-source language model by BirdToast. Features: 31b LLM, VRAM: 0.5GB, LLM Explorer Score: 0.38, ELO: 1451.

Base model:adapter:google/gemm... Base model:google/gemma-4-31b-...   Conversational   Lora   Peft   Region:us   Safetensors   Sft   Trl
Model Card on HF 🤗: https://huggingface.co/BirdToast/Gemma-4-31B-glimmer-rp-v0.2 

Gemma 4 31B Glimmer Rp V0.2 Benchmarks

LMSys ELO 1451 vs 1272 (so35) 14.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 4 31B Glimmer Rp V0.2 Parameters and Internals

LLM NameGemma 4 31B Glimmer Rp V0.2
Repository 🤗https://huggingface.co/BirdToast/Gemma-4-31B-glimmer-rp-v0.2 
Model Namegemma4-31b-it-glimmer-rp-r16a32-v2
Base Model(s)  Gemma 4 31B It   google/gemma-4-31B-it
Model Size31b
Required VRAM0.5 GB
Updated2026-05-20
MaintainerBirdToast
Model Files  0.5 GB
Model ArchitectureAutoModel
Is Biasednone
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modules.|*|l|a|n|g|u|a|g|e|_|m|o|d|e|l|\|.|l|a|y|e|r|s|\|.|\|d|+|\|.|(|s|e|l|f|_|a|t|t|n|\|.|(|q|||k|||v|||o|)|_|p|r|o|j|||m|l|p|\|.|(|g|a|t|e|||u|p|||d|o|w|n|)|_|p|r|o|j|)|$
LoRA Alpha32
LoRA Dropout0
R Param16

Best Alternatives to Gemma 4 31B Glimmer Rp V0.2

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 31B Vore Lora0K / 0 GB470
...31B It Distill Qwen3 0.6B Lora0K / 0 GB50