What are the hardware requirements for Phi 3 Medium Llamaish?

Phi 3 Medium Llamaish requires approximately 28 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi 3 Medium Llamaish and how large is it?

Phi 3 Medium Llamaish is developed by Ba2han, a model with 14b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Phi 3 Medium Llamaish perform on standard benchmarks?

Phi 3 Medium Llamaish has the following published scores: MMLU 77.86. Compare against reference models on this page or on the LLM Explorer leaderboards.

Phi 3 Medium Llamaish by Ba2han — VRAM 28GB, 4K context

Name: Phi 3 Medium Llamaish
Author: Ba2han

Phi 3 Medium Llamaish is an open-source language model by Ba2han. Features: 14b LLM, VRAM: 28GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.13, Arc: 67.4, HellaSwag: 85.6, MMLU: 77.9, GSM8K: 80.4.

Conversational Dataset:ba2han/dollyllama-5k Dataset:sao10k/claude-3-opus-i... En Endpoints compatible Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Ba2han/Phi-3-Medium-Llamaish

Phi 3 Medium Llamaish Parameters and Internals

Model Type

text generation

Additional Notes

GGUF coming soon. (Via Unsloth)

Supported Languages

en (Supported)

Training Details

Data Sources:

Sao10K/Claude-3-Opus-Instruct-15K, Ba2han/DollyLlama-5k

Methodology:

trained mostly on llama-3-70B generated multi-turn conversations with system messages

Input Output

Input Format:

supports system messages

LLM Name	Phi 3 Medium Llamaish
Repository 🤗	https://huggingface.co/Ba2han/Phi-3-Medium-Llamaish
Model Size	14b
Required VRAM	28 GB
Updated	2026-08-25
Maintainer	Ba2han
Model Type	mistral
Instruction-Based	Yes
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 Languages	en
Model Architecture	MistralForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.1
Tokenizer Class	LlamaTokenizer
Padding Token	<\|placeholder6\|>
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the Phi 3 Medium Llamaish capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Phi 3 Medium Llamaish

Best Alternatives	Context / RAM	Downloads	Likes
...ral Nemo Instruct 14B Merge V1	1000K / 24.6 GB	19	0
Phi 3 Medium 4K Instruct	4K / 28 GB	38	28
...2.9.2 Phi 3 Medium Abliterated	4K / 28 GB	9259	19
...2.9.2 Phi 3 Medium Abliterated	4K / 28 GB	8285	24
Phi3 Translator Merged3	4K / 55 GB	6	0
Arsh V1	4K / 28 GB	1123	1
...ll Phi 3 Medium 4K Inst Philos	4K / 28 GB	7	0
...antha2.0 Phi3 Medium Ita 16bit	4K / 28 GB	2604	0
Phi 3 Unsloth Finetune 7	4K / 28 GB	7	0
Phi 3 Unsloth Finetune 6	4K / 28 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than Ba2han/Phi-3-Medium-Llamaish.