LLM EXPLORER 59,358 MODELS INDEXED

Fireball Phi 3 Medium 4K Inst Philos by EpistemeAI2

By EpistemeAI2 · 7 downloads
HF Repo ↗ Copy URL

Fireball Phi 3 Medium 4K Inst Philos is an open-source language model by EpistemeAI2. Features: 14b LLM, VRAM: 28GB, Context: 4K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.23.

  4bit   Conversational   En   Endpoints compatible   Instruct   Mistral   Model-index   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI2/Fireball-Phi-3-medium-4k-inst-Philos 

Fireball Phi 3 Medium 4K Inst Philos Parameters and Internals

LLM NameFireball Phi 3 Medium 4K Inst Philos
Repository 🤗https://huggingface.co/EpistemeAI2/Fireball-Phi-3-medium-4k-inst-Philos 
Base Model(s)  unsloth/phi-3-medium-4k-instruct-bnb-4bit   unsloth/phi-3-medium-4k-instruct-bnb-4bit
Model Size14b
Required VRAM28 GB
Updated2026-07-10
MaintainerEpistemeAI2
Model Typemistral
Instruction-BasedYes
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   3.2 GB: 6-of-6
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Fireball Phi 3 Medium 4K Inst Philos

Best Alternatives
Context / RAM
Downloads
Likes
Arsh V14K / 28 GB11231
...antha2.0 Phi3 Medium Ita 16bit4K / 28 GB26040
Phi 3 Unsloth Finetune 74K / 28 GB70
Phi 3 Unsloth Finetune 64K / 28 GB80
Phi 3 Unsloth Finetune 54K / 28 GB60
Phi 3 Unsloth Finetune 44K / 28 GB80
Phi 3 Unsloth Finetuned 34K / 28 GB60
...ral Nemo Instruct 14B Merge V11000K / 24.6 GB190
Phi 3 Medium 4K Instruct4K / 28 GB3828
...2.9.2 Phi 3 Medium Abliterated4K / 28 GB925919
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI2/Fireball-Phi-3-medium-4k-inst-Philos.