What are the hardware requirements for Mixtral 34Bx2 MoE 60B AWQ?

Mixtral 34Bx2 MoE 60B AWQ requires approximately 32.8 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 Mixtral 34Bx2 MoE 60B AWQ and how large is it?

Mixtral 34Bx2 MoE 60B AWQ is developed by TheBloke, a model with 60.8b 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 Mixtral 34Bx2 MoE 60B AWQ?

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

Mixtral 34Bx2 MoE 60B AWQ by TheBloke — VRAM 32.8GB, 195K context

Name: Mixtral 34Bx2 MoE 60B AWQ
Author: TheBloke

Mixtral 34Bx2 MoE 60B AWQ is an open-source language model by TheBloke. Features: 60.8b LLM, VRAM: 32.8GB, Context: 195K, License: cc-by-nc-4.0, MoE, Quantized, LLM Explorer Score: 0.1.

4-bit Awq Base model:cloudyu/mixtral 34b... Base model:quantized:cloudyu/m... Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/TheBloke/Mixtral_34Bx2_MoE_60B-AWQ

Mixtral 34Bx2 MoE 60B AWQ Parameters and Internals

Model Type

mixtral

Additional Notes

Quantization techniques include AWQ for efficient, low-bit weight usage.

Supported Languages

English (native), Chinese (native)

Input Output

Input Format:

{prompt}

Accepted Modalities:

text

Performance Tips:

For optimal performance, ensure correct installation of required software versions.

LLM Name	Mixtral 34Bx2 MoE 60B AWQ
Repository 🤗	https://huggingface.co/TheBloke/Mixtral_34Bx2_MoE_60B-AWQ
Model Name	Mixtral 34Bx2 MoE 60B
Model Creator	hai
Base Model(s)	Mixtral 34Bx2 MoE 60B cloudyu/Mixtral_34Bx2_MoE_60B
Model Size	60.8b
Required VRAM	32.8 GB
Updated	2026-08-04
Maintainer	TheBloke
Model Type	mixtral
Model Files	9.9 GB: 1-of-4 9.9 GB: 2-of-4 9.9 GB: 3-of-4 3.1 GB: 4-of-4
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	MixtralForCausalLM
License	cc-by-nc-4.0
Context Length	200000
Model Max Length	200000
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	64000
Torch Data Type	float16

Rank the Mixtral 34Bx2 MoE 60B AWQ 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 Mixtral 34Bx2 MoE 60B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
FusionNet 34Bx2 MoE AWQ	32K / 32.8 GB	8	5
...sionNet 34Bx2 MoE V0.1 DPO F16	195K / 121.8 GB	8097	14
60B MoE Coder V3	195K / 121.8 GB	70	3
Mixtral 34Bx2 MoE 60B	195K / 121.9 GB	7876	114
Yi 34Bx2 MoE 60B DPO	195K / 121.8 GB	8035	3
Bagel Hermes 2x34B	195K / 121.9 GB	70	16
Yi 34Bx2 MoE 200K	195K / 121.9 GB	7897	2
Yi 34Bx2 MoE 60B	195K / 121.9 GB	7954	64
...34Bx2 MoE V0.1 Full Linear DPO	195K / 121.8 GB	68	2
FusionNet 34Bx2 MoE V0.1	195K / 121.2 GB	52	8

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Mixtral_34Bx2_MoE_60B-AWQ.