What are the hardware requirements for Cymist2 V01 SFT?

Cymist2 V01 SFT requires approximately 14.4 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 Cymist2 V01 SFT and how large is it?

Cymist2 V01 SFT is developed by cypienai, a model with 7.2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Cymist2 V01 SFT perform on standard benchmarks?

Cymist2 V01 SFT has the following published scores: MMLU 50.19. Compare against reference models on this page or on the LLM Explorer leaderboards.

Cymist2 V01 SFT by cypienai — VRAM 14.4GB, 32K context

Name: Cymist2 V01 SFT
Author: cypienai

Cymist2 V01 SFT is an open-source language model by cypienai. Features: 7.2b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.15, Arc: 47.7, HellaSwag: 76.5, MMLU: 50.2, GSM8K: 16.5.

Arxiv:1910.09700 Conversational Deploy:azure En Endpoints compatible General tasks Mistral Rag Region:us Safetensors Sft Sharded Tensorflow Tr Turkish

Model Card on HF 🤗: https://huggingface.co/cypienai/cymist2-v01-SFT

Cymist2 V01 SFT Parameters and Internals

Model Type

Language Model for Text-Generation

Use Cases

Areas:

General applications requiring Turkish language understanding, RAG and text-generation capabilities

Applications:

Chatbots, virtual assistants, and other AI systems

Limitations:

Not for use in critical systems where incorrect answers could lead to harm

Considerations:

The model, like all AI models, may inherit biases from its training data.

Additional Notes

The model is optimized for text-generation tasks. There is a new version available: cymist-2-v02-SFT.

Supported Languages

Turkish (comprehensive), English (comprehensive)

Training Details

Data Sources:

Diverse set of Turkish & English language sources

Model Architecture:

Leverages the transformers library

LLM Name	Cymist2 V01 SFT
Repository 🤗	https://huggingface.co/cypienai/cymist2-v01-SFT
Base Model(s)	mistralai/Mistral-7B-v0.1 mistralai/Mistral-7B-v0.1
Model Size	7.2b
Required VRAM	14.4 GB
Updated	2026-07-22
Maintainer	cypienai
Model Type	mistral
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Supported Languages	tr en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.1
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Cymist2 V01 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 Cymist2 V01 SFT

Best Alternatives	Context / RAM	Downloads	Likes
...Web AI HumanAI 012 INSTRUCT XA	512K / 14.4 GB	9	0
...Web AI HumanAI 012 INSTRUCT IA	512K / 14.4 GB	8	0
...Web AI HumanAI 011 INSTRUCT ML	512K / 14.4 GB	7	0
14	512K / 14.5 GB	319	0
SpydazWeb HumanAI M2	512K / GB	38	0
...dazWeb AI HumanAI 011 INSTRUCT	512K / 14.4 GB	14	1
SpydazWeb AI HumanAI 009 CHAT	512K / 14.4 GB	6	0
SpydazWeb AI HumanAI 007	512K / 14.4 GB	5	0
...Web AI HumanAI 012 INSTRUCT MX	512K / 14.4 GB	8	0
SpydazWebAI Human AGI 001	512K / 14.4 GB	6	1

Note: green Score (e.g. "73.2") means that the model is better than cypienai/cymist2-v01-SFT.