What are the hardware requirements for MFANN3b SFT?

MFANN3b SFT requires approximately 5.6 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MFANN3b SFT and how large is it?

MFANN3b SFT is developed by netcat420, a model with 2.8b 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 MFANN3b SFT?

MFANN3b SFT is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MFANN3b SFT by netcat420 — VRAM 5.6GB, 128K context

Name: MFANN3b SFT
Author: netcat420

MFANN3b SFT is an open-source language model by netcat420. Features: 2.8b LLM, VRAM: 5.6GB, Context: 128K, Merged, LLM Explorer Score: 0.15.

Merged Model Arxiv:2306.01708 Base model:liminerity/phigment... Base model:netcat420/mfann-lim... Base model:netcat420/mfann3b-r... Endpoints compatible Phi Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/netcat420/MFANN3b-SFT

MFANN3b SFT Parameters and Internals

LLM Name	MFANN3b SFT
Repository 🤗	https://huggingface.co/netcat420/MFANN3b-SFT
Base Model(s)	Phigments12 MFANN Liminerity Slerp 4a MFANN3b Rebase liminerity/Phigments12 netcat420/MFANN-liminerity-slerp-4a netcat420/MFANN3b-Rebase
Merged Model	Yes
Model Size	2.8b
Required VRAM	5.6 GB
Updated	2026-08-02
Maintainer	netcat420
Model Type	phi
Model Files	1.0 GB: 1-of-6 1.0 GB: 2-of-6 1.0 GB: 3-of-6 1.0 GB: 4-of-6 1.0 GB: 5-of-6 0.6 GB: 6-of-6
Model Architecture	PhiForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.47.0
Tokenizer Class	CodeGenTokenizer
Vocabulary Size	51200
Torch Data Type	float16

Rank the MFANN3b SFT 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 MFANN3b SFT

Best Alternatives	Context / RAM	Downloads
MFANN3bv0.24	128K / 11.1 GB	6
MFANN3b	128K / 11.1 GB	86
MFANN3bv1.4	128K / 11.1 GB	8
MFANN Phigments Slerp V3.2	128K / 5.6 GB	6
MFANN3bv1.3	128K / 11.1 GB	14
MFANN3bv0.23	128K / 11.1 GB	10
MFANN3bv1.1	128K / 11.1 GB	10
MFANN3bv1.5	128K / 11.1 GB	8
MFANN Liminerity Slerp 4a	128K / 5.6 GB	7
MFANN3b Rebase	128K / 11.1 GB	7

Note: green Score (e.g. "73.2") means that the model is better than netcat420/MFANN3b-SFT.