arcee-ai_-_raspberry-3B-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
arcee-ai_-_raspberry-3B-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

raspberry-3B - GGUF

Model creator: https://huggingface.co/arcee-ai/
Original model: https://huggingface.co/arcee-ai/raspberry-3B/

Name	Quant method	Size
raspberry-3B.Q2_K.gguf	Q2_K	1.19GB
raspberry-3B.IQ3_XS.gguf	IQ3_XS	1.3GB
raspberry-3B.IQ3_S.gguf	IQ3_S	1.36GB
raspberry-3B.Q3_K_S.gguf	Q3_K_S	1.35GB
raspberry-3B.IQ3_M.gguf	IQ3_M	1.39GB
raspberry-3B.Q3_K.gguf	Q3_K	1.48GB
raspberry-3B.Q3_K_M.gguf	Q3_K_M	1.48GB
raspberry-3B.Q3_K_L.gguf	Q3_K_L	1.59GB
raspberry-3B.IQ4_XS.gguf	IQ4_XS	1.63GB
raspberry-3B.Q4_0.gguf	Q4_0	1.7GB
raspberry-3B.IQ4_NL.gguf	IQ4_NL	1.71GB
raspberry-3B.Q4_K_S.gguf	Q4_K_S	1.71GB
raspberry-3B.Q4_K.gguf	Q4_K	1.8GB
raspberry-3B.Q4_K_M.gguf	Q4_K_M	1.8GB
raspberry-3B.Q4_1.gguf	Q4_1	1.86GB
raspberry-3B.Q5_0.gguf	Q5_0	2.02GB
raspberry-3B.Q5_K_S.gguf	Q5_K_S	2.02GB
raspberry-3B.Q5_K.gguf	Q5_K	2.07GB
raspberry-3B.Q5_K_M.gguf	Q5_K_M	2.07GB
raspberry-3B.Q5_1.gguf	Q5_1	2.18GB
raspberry-3B.Q6_K.gguf	Q6_K	2.36GB
raspberry-3B.Q8_0.gguf	Q8_0	3.06GB

Original model description:

license: other library_name: transformers tags:

generated_from_trainer base_model: Qwen/Qwen2.5-3B license_name: qwen-research license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE model-index:
name: outputs/gelato-3b results: []

Prompt Format: ChatML

This is an experimental which was heavily optimized for reasoning tasks and not meant for production-use.

GGUFs: https://huggingface.co/mradermacher/raspberry-3B-GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	15.40
IFEval (0-Shot)	31.54
BBH (3-Shot)	19.53
MATH Lvl 5 (4-Shot)	7.63
GPQA (0-shot)	3.69
MuSR (0-shot)	9.41
MMLU-PRO (5-shot)	20.60