What are the hardware requirements for Phillama 3.8B V1?

Phillama 3.8B V1 requires approximately 7.6 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 Phillama 3.8B V1 and how large is it?

Phillama 3.8B V1 is developed by raincandy-u, a model with 3.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Phillama 3.8B V1?

Phillama 3.8B V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phillama 3.8B V1 by raincandy-u — VRAM 7.6GB, 4K context

Name: Phillama 3.8B V1
Author: raincandy-u

Phillama 3.8B V1 is an open-source language model by raincandy-u. Features: 3.8b LLM, VRAM: 7.6GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.12.

Conversational Dataset:raincandy-u/dextrometh... Endpoints compatible Instruct Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/raincandy-u/phillama-3.8b-v1

Phillama 3.8B V1 Parameters and Internals

Model Type

text generation

Training Details

Data Sources:

Llama-generated datasets

Methodology:

Trained to be more 'llama-like' and converted into Llama format for compatibility with Llama-2/3 workflows.

Input Output

Input Format:

System prompt and user prompt format as specified

Accepted Modalities:

text

Output Format:

Text based response

LLM Name	Phillama 3.8B V1
Repository 🤗	https://huggingface.co/raincandy-u/phillama-3.8b-v1
Model Size	3.8b
Required VRAM	7.6 GB
Updated	2026-07-30
Maintainer	raincandy-u
Model Type	llama
Instruction-Based	Yes
Model Files	7.6 GB
Model Architecture	LlamaForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.40.0
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the Phillama 3.8B V1 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 Phillama 3.8B V1

Best Alternatives	Context / RAM	Downloads	Likes
Tara 3.8B	146K / 7.6 GB	10	0
...hi3 Unlearning General Methode	128K / 7.6 GB	355	0
Superthoughts Mini V1.3.8B	128K / 7.6 GB	78	1
Phi 3.5 Mini Instruct	128K / 7.6 GB	3544	50
Phi 3 5 Mini Kp 12k Cfr Sft	128K / 7.6 GB	5	0
Phi 3 5 Mini Tictactoe1200	128K / 7.6 GB	8	0
...3 Mini 128K Instruct LLaMAfied	128K / 7.6 GB	11	3
Llamaphi 3 128K Instruct	128K / 7.6 GB	9	1
...i 3 Mini 4K Instruct LLaMAfied	4K / 7.6 GB	15	11
Phillama 3.8B V0.1	4K / 7.6 GB	21	10

Note: green Score (e.g. "73.2") means that the model is better than raincandy-u/phillama-3.8b-v1.