LLM EXPLORER 59,420 MODELS INDEXED

Mixtral 34Bx2 MoE 60B 4.65bpw H6 EXL2 by MatrixC7

By MatrixC7 · 7 downloads

Mixtral 34Bx2 MoE 60B 4.65bpw H6 EXL2 is an open-source language model by MatrixC7. Features: 60b LLM, VRAM: 36.2GB, Context: 195K, License: cc-by-nc-4.0, MoE, Quantized, LLM Explorer Score: 0.1.

  Endpoints compatible   Exl2   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Mixtral 34Bx2 MoE 60B 4.65bpw H6 EXL2 Parameters and Internals

Model Type 
Multimodal, Text Generation
Use Cases 
Areas:
Research, Commercial Applications
Applications:
Natural Language Processing, Causal Language Modeling
Primary Use Cases:
Text Generation, Multilingual Applications
Supported Languages 
English (High), Chinese (High)
Input Output 
Input Format:
Text prompt
Accepted Modalities:
Text
Output Format:
Generated text
LLM NameMixtral 34Bx2 MoE 60B 4.65bpw H6 EXL2
Repository πŸ€—https://huggingface.co/MatrixC7/Mixtral_34Bx2_MoE_60B-4.65bpw-h6-exl2 
Model Size60b
Required VRAM36.2 GB
Updated2026-07-12
MaintainerMatrixC7
Model Typemixtral
Model Files  8.6 GB: 1-of-5   8.6 GB: 2-of-5   8.5 GB: 3-of-5   8.6 GB: 4-of-5   1.9 GB: 5-of-5
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licensecc-by-nc-4.0
Context Length200000
Model Max Length200000
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Mixtral 34Bx2 MoE 60B 4.65bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...i 34Bx2 MoE 60B 6.0bpw H6 EXL2195K / 46.2 GB71
...i 34Bx2 MoE 60B 5.0bpw H6 EXL2195K / 38.8 GB41
... 34Bx2 MoE 60B 2.65bpw H6 EXL2195K / 21.2 GB31
...l 34Bx2 MoE 60B 8.0bpw H8 EXL2195K / 61.3 GB92
...l 34Bx2 MoE 60B 2.4bpw H6 EXL2195K / 19.3 GB73
... 34Bx2 MoE 60B 2.65bpw H6 EXL2195K / 21.2 GB82
...l 34Bx2 MoE 60B EXL2 2.0bpw H8195K / 18.1 GB61
...l 34Bx2 MoE 60B 3.0bpw H6 EXL2195K / 23.8 GB112
...l 34Bx2 MoE 60B 4.0bpw H6 EXL2195K / 31.3 GB92
...l 34Bx2 MoE 60B 6.0bpw H6 EXL2195K / 46.2 GB51
Note: green Score (e.g. "73.2") means that the model is better than MatrixC7/Mixtral_34Bx2_MoE_60B-4.65bpw-h6-exl2.