LLM EXPLORER 59,420 MODELS INDEXED

Phi 4 14B Grpo Limo by mrm8488

By mrm8488 · 7 downloads
HF Repo ↗ Copy URL

Phi 4 14B Grpo Limo is an open-source language model by mrm8488. Features: 14b LLM, VRAM: 29.4GB, Context: 16K, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

  4bit Base model:finetune:unsloth/ph... Base model:unsloth/phi-4-bnb-4...   Conversational   En   Endpoints compatible   Grpo   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/mrm8488/phi-4-14B-grpo-limo 

Phi 4 14B Grpo Limo Parameters and Internals

LLM NamePhi 4 14B Grpo Limo
Repository 🤗https://huggingface.co/mrm8488/phi-4-14B-grpo-limo 
Base Model(s)  Phi 4 Bnb 4bit   unsloth/phi-4-bnb-4bit
Model Size14b
Required VRAM29.4 GB
Updated2026-08-01
Maintainermrm8488
Model Typellama
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.6 GB: 6-of-6
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.48.2
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_87|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi 4 14B Grpo Limo

Best Alternatives
Context / RAM
Downloads
Likes
Parm 2 CoT 14B 16K O1 QwQ16K / 29.4 GB187
Phi 4 14B Grpo Gsm8k 3e16K / 29.4 GB80
...perThoughts CoT 14B 16K O1 QwQ16K / 29.4 GB2656
Heliars Phi4 Carla X1 14B16K / 29.4 GB32
...hts CoT 14B 16K O1 QwQ PyTorch16K / 29.4 GB01
CausalLM 14B EXL28K / 8.5 GB83
...struct 2512 Llamafied TextOnly256K / 27 GB93
...Qwen2.5llamaify 14B V23.3 200K195K / 29.7 GB105
...Qwen2.5llamaify 14B V23.1 200K195K / 29.7 GB151
GeM2 Llamion 14B LongChat195K / 29 GB79154
Note: green Score (e.g. "73.2") means that the model is better than mrm8488/phi-4-14B-grpo-limo.