What are the hardware requirements for Fp3 Llama?

Fp3 Llama requires approximately 8.5 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 Fp3 Llama and how large is it?

Fp3 Llama is developed by YoungPanda, a model with 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 Fp3 Llama?

Fp3 Llama is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Fp3 Llama by YoungPanda — VRAM 8.5GB, 128K context

Name: Fp3 Llama
Author: YoungPanda

Fp3 Llama is an open-source language model by YoungPanda. Features: 8b LLM, VRAM: 8.5GB, Context: 128K, Quantized, LLM Explorer Score: 0.12.

Autotrain compatible Endpoints compatible Ggml Gguf Llama Q8 Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/YoungPanda/fp3_llama

Fp3 Llama Parameters and Internals

LLM Name	Fp3 Llama
Repository 🤗	https://huggingface.co/YoungPanda/fp3_llama
Model Size	8b
Required VRAM	8.5 GB
Updated	2024-08-04
Maintainer	YoungPanda
Model Type	llama
Model Files	32.1 GB 8.5 GB 32.1 GB
GGML Quantization	Yes
GGUF Quantization	Yes
Quantization Type	ggml\|q8\|gguf
Model Architecture	LlamaForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.40.2
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Fp3 Llama 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 Fp3 Llama

Best Alternatives	Context / RAM	Downloads	Likes
...del Llama 3.1 8B Instruct 4bit	128K / 16.1 GB	25	0
...AI Korean Llama 3.1 Sft DPO 8B	128K / 16.1 GB	288	7
...orean Llama3.1 Sft Rlhf DPO 8B	128K / 16.1 GB	94	3
...Ko Llama3 Instruct DPO 8B Base	8K / 16.1 GB	457	0
...nbuddy Llama3 8B V21.1 8K GGUF	8K / 3.2 GB	40	1
... Korean Llama3 Sft DPO 8B Base	8K / 16.1 GB	41	0
...Llama 3 8B Instruct Fine Tuned	8K / 18.8 GB	21	0
Corrector Llama3 Merged	8K / 16.1 GB	20	0
Llama 3 8B Instruct Chinese	8K / 16.1 GB	459	34
...ma 3 Verus 8 Epochs Revision 1	8K / 16.1 GB	110	1

Note: green Score (e.g. "73.2") means that the model is better than YoungPanda/fp3_llama.