What are the hardware requirements for Sft V2?

Sft V2 requires approximately 3.4 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 Sft V2 and how large is it?

Sft V2 is developed by vinmlops, 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 Sft V2?

Sft V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sft V2 by vinmlops — VRAM 3.4GB, 32K context

Name: Sft V2
Author: vinmlops

Sft V2 is an open-source language model by vinmlops. Features: 1.7b LLM, VRAM: 3.4GB, Context: 32K, License: cc-by-nc-4.0, Instruction-Based, LLM Explorer Score: 0.29.

Base model:finetune:vinmlops/c... Base model:vinmlops/cpt-v2 Conversational Educational En Endpoints compatible Instruct Qwen3 Region:us Safetensors Sft Supervised-fine-tuning

Model Card on HF 🤗: https://huggingface.co/vinmlops/sft-v2

Sft V2 Parameters and Internals

LLM Name	Sft V2
Repository 🤗	https://huggingface.co/vinmlops/sft-v2
Base Model(s)	vinmlops/cpt-v2 vinmlops/cpt-v2
Model Size	1.7b
Required VRAM	3.4 GB
Updated	2026-09-27
Maintainer	vinmlops
Model Type	qwen3
Instruction-Based	Yes
Model Files	3.4 GB
Supported Languages	en
Model Architecture	Qwen3ForCausalLM
License	cc-by-nc-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.56.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Sft V2 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 Sft V2

Best Alternatives	Context / RAM	Downloads	Likes
DictaLM 3.0 1.7B Instruct	60K / 3.4 GB	2842	1
RIFA FLASH 1.7B	40K / 3.4 GB	583	0
Pathi Lite Instruct 1.7B	40K / 3.4 GB	0	1
Supertron2 1.7B	40K / 3.4 GB	248	7
Fusionai	40K / 3.4 GB	31	0
...3 1.7B Instruction Noreasoning	40K / 3.4 GB	12020	12
Luth 1.7B Instruct	40K / 3.4 GB	98	14
...ruct Fast CODER Reasoning 2.4B	40K / 9.7 GB	9	1
... Instruct CODER Reasoning 2.7B	40K / 11 GB	8	0
Qwen3 1.7B ShiningValiant3	40K / 6.9 GB	9	5