What are the hardware requirements for Feng 30M?

Feng 30M requires approximately 0.1 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 Feng 30M and how large is it?

Feng 30M is developed by jiaheng0815, a model with 30m 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 Feng 30M?

Feng 30M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Feng 30M by jiaheng0815 — VRAM 0.1GB, 32K context

Name: Feng 30M
Author: jiaheng0815

Feng 30M is an open-source language model by jiaheng0815. Features: 30m LLM, VRAM: 0.1GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.31.

Chinese Conversational Edge-ai Embedded Endpoints compatible Esp32 On-device Qwen3 Region:us Safetensors Tiny-llm Zh

Model Card on HF 🤗: https://huggingface.co/jiaheng0815/feng-30m

Feng 30M Parameters and Internals

LLM Name	Feng 30M
Repository 🤗	https://huggingface.co/jiaheng0815/feng-30m
Model Size	30m
Required VRAM	0.1 GB
Updated	2026-11-05
Maintainer	jiaheng0815
Model Type	qwen3
Model Files	0.1 GB
Supported Languages	zh
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	5.18.0
Tokenizer Class	TokenizersBackend
Vocabulary Size	16384

Rank the Feng 30M 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 Feng 30M

Best Alternatives	Context / RAM	Downloads	Likes
...4b Onpolicy 5k Src30k 35k Cont	256K / 17.6 GB	430	0
...licy 5k Src20k 25k Freeze Rock	256K / 8.9 GB	8	0
...n3 30b A3b To 4b Offpolicy 20k	256K / 17.6 GB	9	0
Qwen3 1.7B Distilled 30B A3B	40K / 4.1 GB	3953	2
Qwen3 30B A3B FP4	40K / 20.7 GB	1201	1
Kintu 2.0 30M	0.5K / 0.1 GB	16	0
Kintu 2.0 30M Base	0.5K / 0.1 GB	13	0