What are the hardware requirements for Faro Yi 9B DPO 6bpw EXL2?

Faro Yi 9B DPO 6bpw EXL2 requires approximately 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 Faro Yi 9B DPO 6bpw EXL2 and how large is it?

Faro Yi 9B DPO 6bpw EXL2 is developed by vikarti-anatra, a model with 9b 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 Faro Yi 9B DPO 6bpw EXL2?

Faro Yi 9B DPO 6bpw EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Faro Yi 9B DPO 6bpw EXL2 by vikarti-anatra — VRAM 7GB, 32K context

Name: Faro Yi 9B DPO 6bpw EXL2
Author: vikarti-anatra

Faro Yi 9B DPO 6bpw EXL2 is an open-source language model by vikarti-anatra. Features: 9b LLM, VRAM: 7GB, Context: 32K, License: mit, Quantized, LLM Explorer Score: 0.12.

Arxiv:2303.08774 6-bit Conversational Dataset:argilla/ultrafeedback-... Dataset:intel/orca dpo pairs Dataset:jondurbin/truthy-dpo-v... Dataset:wenbopan/chinese-dpo-p... En Endpoints compatible Exl2 Llama Quantized Region:us Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/vikarti-anatra/Faro-Yi-9B-DPO-6bpw-exl2

Faro Yi 9B DPO 6bpw EXL2 Parameters and Internals

Model Type

text generation

Additional Notes

Faro-Yi-9B-DPO's responses are favored by GPT-4 Judge in MT-Bench.

Supported Languages

en (proficient), zh (proficient)

Input Output

Performance Tips:

For longer inputs under 24GB of VRAM, use vLLM to have a max prompt of 32K. Set `kv_cache_dtype="fp8_e5m2"` for 48K input length.

LLM Name	Faro Yi 9B DPO 6bpw EXL2
Repository 🤗	https://huggingface.co/vikarti-anatra/Faro-Yi-9B-DPO-6bpw-exl2
Model Size	9b
Required VRAM	7 GB
Updated	2026-08-03
Maintainer	vikarti-anatra
Model Type	llama
Model Files	7.0 GB
Supported Languages	en zh
Quantization Type	exl2
Model Architecture	LlamaForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Rank the Faro Yi 9B DPO 6bpw EXL2 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 Faro Yi 9B DPO 6bpw EXL2

Best Alternatives	Context / RAM	Downloads	Likes
Yi 9B 200K 3.0bpw H6 EXL2	256K / 3.9 GB	6	1
Yi 9B 200K 6.0bpw H6 EXL2	256K / 7 GB	3	1
Faro Yi 9B DPO 8bpw EXL2	32K / 8.3 GB	2	1
...5 9B Chat Quantized Merge 4Bit	7K / 34 GB	6	0
Master Yi 9B 8.0bpw H8 EXL2	4K / 8.7 GB	3	2
Master Yi 9B 3.0bpw H6 EXL2	4K / 3.9 GB	4	1
Master Yi 9B 5.0bpw H6 EXL2	4K / 5.9 GB	4	1
Master Yi 9B 4.0bpw H6 EXL2	4K / 4.9 GB	3	1
Master Yi 9B 6.0bpw H6 EXL2	4K / 7 GB	3	1
Yi 1.5 9B 8bit	4K / 9.3 GB	7	1

Note: green Score (e.g. "73.2") means that the model is better than vikarti-anatra/Faro-Yi-9B-DPO-6bpw-exl2.