What are the hardware requirements for Phi Filtered 500M C1?

Phi Filtered 500M C1 requires approximately 0.7 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi Filtered 500M C1 and how large is it?

Phi Filtered 500M C1 is developed by rwitz2, a model with 1b 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 Phi Filtered 500M C1?

Phi Filtered 500M C1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi Filtered 500M C1 by rwitz2 — VRAM 0.7GB, 2K context

Name: Phi Filtered 500M C1
Author: rwitz2

Phi Filtered 500M C1 is an open-source language model by rwitz2. Features: 1b LLM, VRAM: 0.7GB, Context: 2K, LLM Explorer Score: 0.13.

Arxiv:1910.09700 Conversational Endpoints compatible Mistral Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/rwitz2/phi-filtered-500m-c1

Phi Filtered 500M C1 Parameters and Internals

LLM Name	Phi Filtered 500M C1
Repository 🤗	https://huggingface.co/rwitz2/phi-filtered-500m-c1
Model Size	1b
Required VRAM	0.7 GB
Updated	2026-06-09
Maintainer	rwitz2
Model Type	mistral
Model Files	0.7 GB
Model Architecture	MistralForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.41.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|placeholder6\|>
Vocabulary Size	32064
Torch Data Type	bfloat16

Rank the Phi Filtered 500M C1 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 Phi Filtered 500M C1

Best Alternatives	Context / RAM	Downloads	Likes
Ganga 1B	128K / 4 GB	28	21
Biinduct 1B Baseline	32K / 2.2 GB	11	0
MD Judge V0.1	32K / 14.4 GB	377	18
Nucleus 1B Alpha 1	32K / 2.3 GB	8	12
Mallam 1.1B 20K Instructions	32K / 2.2 GB	67	1
Experimental Mistral 1B V00	32K / 3.5 GB	105	3
Lmlab Mistral 1B Untrained	32K / 4.5 GB	35	7
Empty Phi 1B	3K / 5.8 GB	5	0
Nucleus 1B GPTQ	32K / 1 GB	5	1
Mistral 1B GPTQ	32K / 1 GB	7	0

Note: green Score (e.g. "73.2") means that the model is better than rwitz2/phi-filtered-500m-c1.