What are the hardware requirements for Yi 34Bx2 MoE 60B GGUF?

Yi 34Bx2 MoE 60B GGUF requires approximately 0.3 GB of VRAM and supports a context window of 195K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Yi 34Bx2 MoE 60B GGUF and how large is it?

Yi 34Bx2 MoE 60B GGUF is developed by second-state, a model with 60b 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 Yi 34Bx2 MoE 60B GGUF?

Yi 34Bx2 MoE 60B GGUF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Yi 34Bx2 MoE 60B GGUF by second-state — VRAM 0.3GB, 195K context

Name: Yi 34Bx2 MoE 60B GGUF
Author: second-state

Yi 34Bx2 MoE 60B GGUF is an open-source language model by second-state. Features: 60b LLM, VRAM: 0.3GB, Context: 195K, License: cc-by-nc-4.0, MoE, Quantized, LLM Explorer Score: 0.11.

Base model:cloudyu/yi-34bx2-mo... Base model:quantized:cloudyu/y... Conversational Endpoints compatible Fp16 Gguf Mixtral Moe Q2 Q8 0 Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF

Yi 34Bx2 MoE 60B GGUF Parameters and Internals

Model Type

mistral

Additional Notes

Quantized by Second State Inc. Quantization methods include Q2_K, Q3_K_L, Q3_K_M, Q3_K_S, Q4_0, Q4_K_M, Q4_K_S, Q5_0, Q5_K_M, Q5_K_S, Q6_K, Q8_0, and f16.

LLM Name	Yi 34Bx2 MoE 60B GGUF
Repository 🤗	https://huggingface.co/second-state/Yi-34Bx2-MoE-60B-GGUF
Model Name	Yi 34Bx2 MoE 60B
Model Creator	cloudyu
Base Model(s)	Yi 34Bx2 MoE 60B cloudyu/Yi-34Bx2-MoE-60B
Model Size	60b
Required VRAM	0.3 GB
Updated	2026-05-20
Maintainer	second-state
Model Type	mistral
Model Files	22.4 GB 31.8 GB 29.2 GB 26.3 GB 34.3 GB 36.7 GB 34.6 GB 41.9 GB 43.1 GB 41.9 GB 49.9 GB 32.2 GB: 1-of-3 32.1 GB: 2-of-3 0.3 GB: 3-of-3 31.9 GB: 1-of-8 31.7 GB: 2-of-8 31.7 GB: 3-of-8 31.7 GB: 4-of-8 31.7 GB: 5-of-8 31.7 GB: 6-of-8 31.7 GB: 7-of-8 21.1 GB: 8-of-8
GGUF Quantization	Yes
Quantization Type	fp16\|gguf\|q2\|q8_0\|q4_k\|q5_k
Model Architecture	MixtralForCausalLM
License	cc-by-nc-4.0
Context Length	200000
Model Max Length	200000
Transformers Version	4.36.2
Vocabulary Size	64000
Torch Data Type	bfloat16

Rank the Yi 34Bx2 MoE 60B GGUF 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 Yi 34Bx2 MoE 60B GGUF

Best Alternatives	Context / RAM	Downloads	Likes
...i 34Bx2 MoE 60B 6.0bpw H6 EXL2	195K / 46.2 GB	7	1
...i 34Bx2 MoE 60B 5.0bpw H6 EXL2	195K / 38.8 GB	4	1
... 34Bx2 MoE 60B 2.65bpw H6 EXL2	195K / 21.2 GB	3	1
...l 34Bx2 MoE 60B 8.0bpw H8 EXL2	195K / 61.3 GB	9	2
...l 34Bx2 MoE 60B 2.4bpw H6 EXL2	195K / 19.3 GB	7	3
... 34Bx2 MoE 60B 4.65bpw H6 EXL2	195K / 36.2 GB	7	1
... 34Bx2 MoE 60B 2.65bpw H6 EXL2	195K / 21.2 GB	8	2
...l 34Bx2 MoE 60B EXL2 2.0bpw H8	195K / 18.1 GB	6	1
...l 34Bx2 MoE 60B 3.0bpw H6 EXL2	195K / 23.8 GB	11	2
...l 34Bx2 MoE 60B 4.0bpw H6 EXL2	195K / 31.3 GB	9	2