What are the hardware requirements for Felsefe Ft V1?

Felsefe Ft V1 requires approximately 0.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Felsefe Ft V1 and how large is it?

Felsefe Ft V1 is developed by heraklestech, a model with 4b 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 Felsefe Ft V1?

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

Felsefe Ft V1 by heraklestech — VRAM 0.1GB

Name: Felsefe Ft V1
Author: heraklestech

Felsefe Ft V1 is an open-source language model by heraklestech. Features: 4b LLM, VRAM: 0.1GB, Quantized, LLM Explorer Score: 0.28.

Arxiv:1910.09700 4bit Base model:adapter:unsloth/qwe... Base model:unsloth/qwen3-4b-un... Conversational Lora Peft Quantized Region:us Safetensors Sft Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/heraklestech/felsefe-ft-v1

Felsefe Ft V1 Parameters and Internals

LLM Name	Felsefe Ft V1
Repository 🤗	https://huggingface.co/heraklestech/felsefe-ft-v1
Base Model(s)	Qwen3 4B Unsloth Bnb 4bit unsloth/Qwen3-4B-unsloth-bnb-4bit
Model Size	4b
Required VRAM	0.1 GB
Updated	2026-09-30
Maintainer	heraklestech
Model Files	0.1 GB
Quantization Type	4bit
Model Architecture	AutoModel
Model Max Length	40960
Is Biased	none
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|vision_pad\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	k_proj\|o_proj\|gate_proj\|down_proj\|v_proj\|up_proj\|q_proj
LoRA Alpha	32
LoRA Dropout	0
R Param	16
Errors	replace

Rank the Felsefe Ft 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 Felsefe Ft V1

Best Alternatives	Context / RAM	Downloads	Likes
QiFu V1	0K / 0.2 GB	64	1
...istill Haiku Sftv4 Nofilter V1	0K / 0.5 GB	5	0
AuraGo Qwen3.5 4B	256K / 9.3 GB	16	0
Yield Ai Qwen3.5 4B	0K / 0 GB	14	1
Qwen3 4B Halo Expert	0K / 0.3 GB	17	1
...n3vl 4B Lora No Height R64 Vit	0K / 0.3 GB	13	1
... 4B Lora No Parameters R64 Vit	0K / 0.3 GB	12	1
Qwen3vl 4B Lora No Fov R64 Vit	0K / 0.3 GB	11	1
...B Thinking Agentic Coding GSPO	0K / 0 GB	53	0
... 3n 4B It Distill Smollm2 360M	0K / 0 GB	55	0