LLM EXPLORER 59,358 MODELS INDEXED

Phi4 MedIT 10B O1 by mkurman

By mkurman · 27 downloads

Phi4 MedIT 10B O1 is an open-source language model by mkurman. Features: 10b LLM, VRAM: 20.6GB, Context: 16K, License: mit, Quantized, LLM Explorer Score: 0.21.

  Arxiv:2412.08905   Chat   Code   Conversational   Custom code   En   Endpoints compatible   Gguf   Llama   Math   Phi   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Phi4 MedIT 10B O1 Parameters and Internals

LLM NamePhi4 MedIT 10B O1
Repository πŸ€—https://huggingface.co/mkurman/phi4-MedIT-10B-o1 
Model Size10b
Required VRAM20.6 GB
Updated2026-08-02
Maintainermkurman
Model Typellama
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   5.0 GB: 3-of-5   4.6 GB: 4-of-5   1.0 GB: 5-of-5   10.9 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.46.2
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi4 MedIT 10B O1

Best Alternatives
Context / RAM
Downloads
Likes
Falcon3 10B Instruct 1.58bit32K / 4 GB42227
...truct Gptqmodel 4bit Vortex V132K / 5.6 GB93
...enbuddy Falcon3 10B V24.2 131K128K / 20.7 GB60
Priya 10B128K / 20.5 GB112
HelpingAI2.5 10B128K / 20.5 GB662
L3.1 Mochav2 10B128K / 42.8 GB210
HELVETE X128K / 20.5 GB10411
HelpingAI2.5 10B128K / 20.5 GB98
Yarn Solar 10B 64K64K / 21.4 GB15016
StoryTeller 10B 2e V258K / 21.4 GB51
Note: green Score (e.g. "73.2") means that the model is better than mkurman/phi4-MedIT-10B-o1.