What are the hardware requirements for Qwen3 1.7B SPFT Ultrafeedback?

Qwen3 1.7B SPFT Ultrafeedback requires approximately 3.4 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 1.7B SPFT Ultrafeedback and how large is it?

Qwen3 1.7B SPFT Ultrafeedback is developed by pvdhihihi, a model with 1.7b 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 Qwen3 1.7B SPFT Ultrafeedback?

Qwen3 1.7B SPFT Ultrafeedback is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 1.7B SPFT Ultrafeedback by pvdhihihi — VRAM 3.4GB, 40K context

Name: Qwen3 1.7B SPFT Ultrafeedback
Author: pvdhihihi

Qwen3 1.7B SPFT Ultrafeedback is an open-source language model by pvdhihihi. Features: 1.7b LLM, VRAM: 3.4GB, Context: 40K, License: apache-2.0.

Alignment-handbook Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-1.7b Conversational Dataset:huggingfaceh4/ultrafee... Endpoints compatible Generated from trainer Qwen3 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/pvdhihihi/Qwen3-1.7B-SPFT-ultrafeedback

Qwen3 1.7B SPFT Ultrafeedback Parameters and Internals

LLM Name	Qwen3 1.7B SPFT Ultrafeedback
Repository 🤗	https://huggingface.co/pvdhihihi/Qwen3-1.7B-SPFT-ultrafeedback
Base Model(s)	Qwen/Qwen3-1.7B Qwen/Qwen3-1.7B
Model Size	1.7b
Required VRAM	3.4 GB
Updated	2026-10-17
Maintainer	pvdhihihi
Model Type	qwen3
Model Files	3.4 GB 0.0 GB
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	40960
Model Max Length	40960
Transformers Version	4.51.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen3 1.7B SPFT Ultrafeedback 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 Qwen3 1.7B SPFT Ultrafeedback

Best Alternatives	Context / RAM	Downloads	Likes
Lucy 128K	128K / 3.4 GB	123	112
Polaris 1.7B Preview	128K / 3.4 GB	73	8
DictaLM 3.0 1.7B Instruct	60K / 3.4 GB	2842	1
Boole 1.7B	40K / 0.2 GB	539	9
Qwen3 1.7B	40K / 4 GB	5633291	500
Stormdesk Triage	40K / 3.4 GB	461	1
CORe Pico 4	40K / 3.4 GB	895	2
Finnai Slm V4	40K / 3.4 GB	226	0
CORe Pico V3	40K / 3.4 GB	720	0
ALoDLM 1.7B	40K / 4.1 GB	77	6

Note: green Score (e.g. "73.2") means that the model is better than pvdhihihi/Qwen3-1.7B-SPFT-ultrafeedback.