What are the hardware requirements for Model 4?

Model 4 requires approximately 3.6 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 Model 4 and how large is it?

Model 4 is developed by Sakalti, 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 Model 4?

Model 4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Model 4 by Sakalti — VRAM 3.6GB, 128K context

Name: Model 4
Author: Sakalti

Model 4 is an open-source language model by Sakalti. Features: 1.5b LLM, VRAM: 3.6GB, Context: 128K, License: apache-2.0, Merged, LLM Explorer Score: 0.15.

Merged Model Arxiv:2306.01708 Base model:qwen/qwen2.5-1.5b Base model:qwen/qwen2.5-1.5b-i... Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Sakalti/model-4

Model 4 Parameters and Internals

LLM Name	Model 4
Repository 🤗	https://huggingface.co/Sakalti/model-4
Base Model(s)	Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B Qwen/Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B
Merged Model	Yes
Model Size	1.5b
Required VRAM	3.6 GB
Updated	2026-08-08
Maintainer	Sakalti
Model Type	qwen2
Model Files	1.0 GB: 1-of-4 1.0 GB: 2-of-4 1.0 GB: 3-of-4 0.6 GB: 4-of-4
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.45.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Model 4 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 Model 4

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 1.5B 1.3M Stretched	1280K / 3.1 GB	21	0
ReaderLM V2	500K / 3.1 GB	35356	804
Reader Lm 1.5B	250K / 3.1 GB	385	608
DeepSeek R1 Distill Qwen 1.5B	128K / 3.5 GB	600051	1545
Pulsar Coder V1	128K / 3.1 GB	291	1
MLR Executor Qwen 1.5B	128K / 3.5 GB	503	0
Ko R1 1.5B Preview	128K / 7.1 GB	8	9
Axiom Python 1.5B	128K / 3.1 GB	312	0
...2 1.5B Lora Tensorboard Merged	128K / 3.1 GB	127	1
Qwen2.5 1.5B	128K / 3.1 GB	863295	203

Note: green Score (e.g. "73.2") means that the model is better than Sakalti/model-4.