What are the hardware requirements for 1.5B Policy Iteration 4?

1.5B Policy Iteration 4 requires approximately 3.1 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 1.5B Policy Iteration 4 and how large is it?

1.5B Policy Iteration 4 is developed by AngelRaychev, 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 1.5B Policy Iteration 4?

1.5B Policy Iteration 4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

1.5B Policy Iteration 4 by AngelRaychev — VRAM 3.1GB, 128K context

Name: 1.5B Policy Iteration 4
Author: AngelRaychev

1.5B Policy Iteration 4 is an open-source language model by AngelRaychev. Features: 1.5b LLM, VRAM: 3.1GB, Context: 128K, LLM Explorer Score: 0.18.

Base model:angelraychev/1.5b-p... Base model:finetune:angelraych... Conversational Endpoints compatible Generated from trainer Pytorch Qwen2 Region:us Sft Trl

Model Card on HF 🤗: https://huggingface.co/AngelRaychev/1.5B-policy-iteration_4

1.5B Policy Iteration 4 Parameters and Internals

LLM Name	1.5B Policy Iteration 4
Repository 🤗	https://huggingface.co/AngelRaychev/1.5B-policy-iteration_4
Model Name	1.5B-policy-iteration_4
Base Model(s)	AngelRaychev/1.5B-policy-iteration_3 AngelRaychev/1.5B-policy-iteration_3
Model Size	1.5b
Required VRAM	3.1 GB
Updated	2026-08-21
Maintainer	AngelRaychev
Model Type	qwen2
Model Files	3.1 GB 0.0 GB
Model Architecture	Qwen2ForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.51.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the 1.5B Policy Iteration 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 1.5B Policy Iteration 4

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 1.5B 1.3M Stretched	1280K / 3.1 GB	12	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
Ko R1 1.5B Preview	128K / 7.1 GB	8	9
Qwen2.5 1.5B	128K / 3.1 GB	863295	203
Merge Cord V1	128K / 3.1 GB	155	1
VibeThinker 1.5B	128K / 3.5 GB	3417	552
...FT Tulu3 Decontaminated Masked	128K / 3.1 GB	167	0
Qwen2 1.5B	128K / 3.1 GB	195380	102

Note: green Score (e.g. "73.2") means that the model is better than AngelRaychev/1.5B-policy-iteration_4.