What are the hardware requirements for Qwen1.5 1.8B Seed Sft?

Qwen1.5 1.8B Seed Sft requires approximately 3.7 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 Qwen1.5 1.8B Seed Sft and how large is it?

Qwen1.5 1.8B Seed Sft is developed by WDong, a model with 1.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Qwen1.5 1.8B Seed Sft perform on standard benchmarks?

Qwen1.5 1.8B Seed Sft has the following published scores: MMLU 24.54. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen1.5 1.8B Seed Sft by WDong — VRAM 3.7GB, 32K context

Name: Qwen1.5 1.8B Seed Sft
Author: WDong

Qwen1.5 1.8B Seed Sft is an open-source language model by WDong. Features: 1.8b LLM, VRAM: 3.7GB, Context: 32K, License: mit, LLM Explorer Score: 0.17, Arc: 24.7, HellaSwag: 29.6, MMLU: 24.5.

Arxiv:2401.10020 Conversational En Endpoints compatible Qwen2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/WDong/qwen1.5-1.8B-seed-sft

Qwen1.5 1.8B Seed Sft Parameters and Internals

Model Type

transformer-based decoder-only

Additional Notes

This model is an SFT version of Qwen1.5, a transformer-based decoder-only language model. Performance improvement in Chat models and stable support of 32K context length. Multilingual support for both base and chat models.

Supported Languages

English (Multilingual support)

LLM Name	Qwen1.5 1.8B Seed Sft
Repository 🤗	https://huggingface.co/WDong/qwen1.5-1.8B-seed-sft
Model Size	1.8b
Required VRAM	3.7 GB
Updated	2026-07-06
Maintainer	WDong
Model Type	qwen2
Model Files	3.7 GB
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen1.5 1.8B Seed Sft 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 Qwen1.5 1.8B Seed Sft

Best Alternatives	Context / RAM	Downloads	Likes
Palmyra Mini Thinking B	128K / 3.5 GB	35	27
Dhanishtha	128K / 3.5 GB	82	2
LaConfiance PRYMMAL ECE TW3	128K / 7.1 GB	6	0
Reyna Mini 1.8B V0.1	32K / 3.7 GB	66	2
Qwen1.5 1.8B Chat	32K / 3.7 GB	66688	75
Qwen1.5 1.8B	32K / 3.7 GB	67455	59
Qwen1.5 1.8B Chat Heretic	32K / 3.7 GB	8	0
Qwen1.5 1.8B Chat Heretic	32K / 3.7 GB	6	0
Colegium Ai 1.8B	32K / 3.7 GB	6	0
Qwen Fine Tuned V0	32K / 3.7 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than WDong/qwen1.5-1.8B-seed-sft.