What are the hardware requirements for Qwen3 Sft Feedback With Proof Repair?

Qwen3 Sft Feedback With Proof Repair requires approximately 16.4 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 Qwen3 Sft Feedback With Proof Repair and how large is it?

Qwen3 Sft Feedback With Proof Repair is developed by formalmathatepfl, a model with 8.2b 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 Sft Feedback With Proof Repair?

Qwen3 Sft Feedback With Proof Repair is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 Sft Feedback With Proof Repair by formalmathatepfl — VRAM 16.4GB, 32K context

Name: Qwen3 Sft Feedback With Proof Repair
Author: formalmathatepfl

Qwen3 Sft Feedback With Proof Repair is an open-source language model by formalmathatepfl. Features: 8.2b LLM, VRAM: 16.4GB, Context: 32K, License: other, LLM Explorer Score: 0.33.

Base model:finetune:formalmath... Base model:formalmathatepfl/qw... Conversational Endpoints compatible Full Generated from trainer Llama-factory Qwen3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/formalmathatepfl/qwen3-sft-feedback-with-proof-repair

Qwen3 Sft Feedback With Proof Repair Parameters and Internals

LLM Name	Qwen3 Sft Feedback With Proof Repair
Repository 🤗	https://huggingface.co/formalmathatepfl/qwen3-sft-feedback-with-proof-repair
Base Model(s)	Qwen3 Cpt formalmathatepfl/qwen3-cpt
Model Size	8.2b
Required VRAM	16.4 GB
Updated	2026-08-31
Maintainer	formalmathatepfl
Model Type	qwen3
Model Files	4.9 GB: 1-of-4 4.9 GB: 2-of-4 5.0 GB: 3-of-4 1.6 GB: 4-of-4 0.0 GB
Model Architecture	Qwen3ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.57.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Qwen3 Sft Feedback With Proof Repair 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 Sft Feedback With Proof Repair

Best Alternatives	Context / RAM	Downloads	Likes
...nical Understanding Model V2.1	128K / 16.4 GB	10	0
...en 3 Panda Agi 3.3 DPO 8epochs	80K / 16.4 GB	71	0
Intern S1 Mini Lm	64K / 16.4 GB	307	0
Ice AI	40K / 16.4 GB	857	5
Diallm Qwen Sft Aus	40K / 16.4 GB	46	0
Diallm Qwen Sft Brit	40K / 16.4 GB	36	0
Diallm Qwen Sft All	40K / 16.4 GB	7	0
Diallm Qwen Sft Ind	40K / 16.4 GB	5	0
S V3 1ep	40K / 16.4 GB	7	0
...wen Hook Layer 9 Posneg Merged	40K / 16.4 GB	42	0

Note: green Score (e.g. "73.2") means that the model is better than formalmathatepfl/qwen3-sft-feedback-with-proof-repair.