What are the hardware requirements for Soulbox Cbt Therapy 1.5B?

Soulbox Cbt Therapy 1.5B requires approximately 2.8 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Soulbox Cbt Therapy 1.5B and how large is it?

Soulbox Cbt Therapy 1.5B is developed by kakashi3lite, a model with 1.5b 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 Soulbox Cbt Therapy 1.5B?

Soulbox Cbt Therapy 1.5B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Soulbox Cbt Therapy 1.5B by kakashi3lite — VRAM 2.8GB, 32K context

Name: Soulbox Cbt Therapy 1.5B
Author: kakashi3lite

Soulbox Cbt Therapy 1.5B is an open-source language model by kakashi3lite. Features: 1.5b LLM, VRAM: 2.8GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based.

Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-1.5b-i... Cbt Cognitive-behavioral-therapy Conversational Dataset:kakashi3lite/soulbox-c... Dora Edge-deployment Endpoints compatible Gguf Guardrail Hi Hindi Instruct Llama.cpp Low-resource Marathi Mental-health Mlx Model-index Mr Multilingual Pytorch Quantized Qwen Qwen2 Qwen2.5 Region:us Safetensors Self-consistency Sharded Te Telugu Tensorflow Therapy

Model Card on HF 🤗: https://huggingface.co/kakashi3lite/soulbox-cbt-therapy-1.5b

Soulbox Cbt Therapy 1.5B Parameters and Internals

LLM Name	Soulbox Cbt Therapy 1.5B
Repository 🤗	https://huggingface.co/kakashi3lite/soulbox-cbt-therapy-1.5b
Base Model(s)	Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct
Model Size	1.5b
Required VRAM	2.8 GB
Updated	2026-08-09
Maintainer	kakashi3lite
Model Type	qwen2
Instruction-Based	Yes
Model Files	0.5 GB: 1-of-9 0.3 GB: 2-of-9 0.3 GB: 3-of-9 0.3 GB: 4-of-9 0.3 GB: 5-of-9 0.3 GB: 6-of-9 0.3 GB: 7-of-9 0.3 GB: 8-of-9 0.2 GB: 9-of-9 1.0 GB
Supported Languages	hi mr te
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	5.9.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Soulbox Cbt Therapy 1.5B 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 Soulbox Cbt Therapy 1.5B

Best Alternatives	Context / RAM	Downloads
Atem V1.1.5B	32K / 1 GB	126
Qwen2 1.5B Instruct GGUF	32K / 0.7 GB	439
Qwen2 1.5B Instruct GGUF	32K / 0.7 GB	42
Legal Qwen2.5 1.5B Sft	32K / 3.1 GB	1031
Legal Chatbot Qwen2.5 1.5B Sft	32K / 3.1 GB	871
....5B Instruct Legal Chatbot Sft	32K / 3.1 GB	592
Qwen2.5 1.5B Legal Sft	32K / 3.1 GB	677
Legal Chatbot Qwen2.5 1.5B Sft	32K / 3.1 GB	506
... 2.5 1.5B Indonesian Legal Sft	32K / 3.1 GB	454
...wen2.5 1.5B Legal Id Finetuned	32K / 3.1 GB	345

Note: green Score (e.g. "73.2") means that the model is better than kakashi3lite/soulbox-cbt-therapy-1.5b.