LLM EXPLORER 59,420 MODELS INDEXED

MixTAO 7Bx2 MoE V8.1 AWQ by Ichigo2899

By Ichigo2899 · 5 downloads

MixTAO 7Bx2 MoE V8.1 AWQ is an open-source language model by Ichigo2899. Features: 12.9b LLM, VRAM: 7.1GB, Context: 32K, MoE, Quantized, LLM Explorer Score: 0.11.

  4-bit   Awq   Endpoints compatible   Mixtral   Moe   Quantized   Region:us   Safetensors

MixTAO 7Bx2 MoE V8.1 AWQ Parameters and Internals

LLM NameMixTAO 7Bx2 MoE V8.1 AWQ
Repository πŸ€—https://huggingface.co/Ichigo2899/MixTAO-7Bx2-MoE-v8.1-AWQ 
Model Size12.9b
Required VRAM7.1 GB
Updated2026-08-02
MaintainerIchigo2899
Model Typemixtral
Model Files  7.1 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMixtralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to MixTAO 7Bx2 MoE V8.1 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...r Dolphin Mixtral 2x7b DPO AWQ32K / 7.1 GB51
...Grc FusionNet 7Bx2 MoE 13B AWQ32K / 7.1 GB73
...r Dolphin Mixtral 2x7b DPO AWQ32K / 7.1 GB89
Mixtral 7Bx2 MoE AWQ32K / 7.1 GB2502
Blue Orchid 2x7b AWQ8K / 7.1 GB31
MixTAO 7Bx2 MoE V8.132K / 25.8 GB1538156
Inf Silent Kunoichi V0.1 2x7B32K / 25.6 GB80
Inf Silent Kunoichi V0.2 2x7B32K / 25.6 GB91
LogoS 7Bx2 MoE 13B V0.232K / 25.9 GB797810
MixTAO 7Bx2 MoE V8.132K / 25.8 GB876052
Note: green Score (e.g. "73.2") means that the model is better than Ichigo2899/MixTAO-7Bx2-MoE-v8.1-AWQ.