What are the hardware requirements for Numfalm Chat Full?

Numfalm Chat Full requires approximately 7.3 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Numfalm Chat Full and how large is it?

Numfalm Chat Full is developed by wannaphong, a model with 3.6b 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 Numfalm Chat Full?

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

Numfalm Chat Full by wannaphong — VRAM 7.3GB, 2K context

Name: Numfalm Chat Full
Author: wannaphong

Numfalm Chat Full is an open-source language model by wannaphong. Features: 3.6b LLM, VRAM: 7.3GB, Context: 2K, LLM Explorer Score: 0.12.

Arxiv:1910.09700 Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/wannaphong/numfalm-chat-full

Numfalm Chat Full Parameters and Internals

LLM Name	Numfalm Chat Full
Repository 🤗	https://huggingface.co/wannaphong/numfalm-chat-full
Model Size	3.6b
Required VRAM	7.3 GB
Updated	2026-06-07
Maintainer	wannaphong
Model Type	llama
Model Files	5.0 GB: 1-of-2 2.3 GB: 2-of-2
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.38.1
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	64256
Torch Data Type	bfloat16

Rank the Numfalm Chat Full 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 Numfalm Chat Full

Best Alternatives	Context / RAM	Downloads	Likes
Coder0.1.3	128K / 7.2 GB	6	0
Keyframer2	128K / 7.2 GB	8	0
ColdBrew Aphid	128K / 7.2 GB	1	1
Testing Semifinal	128K / 7.3 GB	8	0
...kpoint 1314 DPO Checkpoint 747	2K / 7.3 GB	12	0
...ckpoint 564 DPO Checkpoint 249	2K / 7.3 GB	27	0
... ChatMusician Bnb 4bit Smashed	2K / 4.2 GB	17	0

Note: green Score (e.g. "73.2") means that the model is better than wannaphong/numfalm-chat-full.