LLM EXPLORER 59,420 MODELS INDEXED

Phi4 Reasoning Merged by ykarout

By ykarout · 4 downloads
HF Repo ↗ Copy URL

Phi4 Reasoning Merged is an open-source language model by ykarout. Features: 14.7b LLM, VRAM: 29.4GB, Context: 16K, License: apache-2.0, LLM Explorer Score: 0.17.

Base model:finetune:unsloth/ph...   Base model:unsloth/phi-4   Conversational   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/ykarout/phi4-reasoning-merged 

Phi4 Reasoning Merged Parameters and Internals

LLM NamePhi4 Reasoning Merged
Repository 🤗https://huggingface.co/ykarout/phi4-reasoning-merged 
Base Model(s)  unsloth/Phi-4   unsloth/Phi-4
Model Size14.7b
Required VRAM29.4 GB
Updated2026-07-26
Maintainerykarout
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
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.50.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_87|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi4 Reasoning Merged

Best Alternatives
Context / RAM
Downloads
Likes
...kpoints 511 Onlytrainex Merged31K / 29.4 GB250
...ruct Extended 3500steps Merged31K / 29.4 GB710
E2 Phi4 Instruct NTK Scaled31K / 29.4 GB200
...ct NTK Scaled 1000steps Merged31K / 29.4 GB50
Phi 416K / 29.4 GB153991
Luminis Phi 416K / 29.5 GB151713
Tea16K / 29.4 GB3242
Phi 4 Sce Exp V0.116K / 29.5 GB91
Phi 4 RR Shoup16K / 29.5 GB62
Phi 4 RStock V0.116K / 29.5 GB80
Note: green Score (e.g. "73.2") means that the model is better than ykarout/phi4-reasoning-merged.