LLM EXPLORER 60,062 MODELS INDEXED

Nexus 4x7B IKM MLX by Severian

By Severian · 64 downloads
HF Repo ↗ Copy URL

Nexus 4x7B IKM MLX is an open-source language model by Severian. Features: LLM, VRAM: 48.3GB, Context: 32K, License: mit, MoE, LLM Explorer Score: 0.11.

Dataset:severian/internal-know...   Endpoints compatible   Mixtral   Moe   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Severian/Nexus-4x7B-IKM-MLX 

Nexus 4x7B IKM MLX Parameters and Internals

Model Type 
knowledge mapping, problem-solving
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
comprehensive understanding, reasoning in diverse domains
Training Details 
Data Sources:
Internal Knowledge Map
Methodology:
fine-tuning
LLM NameNexus 4x7B IKM MLX
Repository 🤗https://huggingface.co/Severian/Nexus-4x7B-IKM-MLX 
Required VRAM48.3 GB
Updated2026-07-23
MaintainerSeverian
Model Typemixtral
Model Files  5.3 GB: 1-of-10   5.3 GB: 2-of-10   5.3 GB: 3-of-10   5.3 GB: 4-of-10   5.3 GB: 5-of-10   5.3 GB: 6-of-10   5.3 GB: 7-of-10   5.3 GB: 8-of-10   5.3 GB: 9-of-10   0.6 GB: 10-of-10
Model ArchitectureMixtralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Nexus 4x7B IKM MLX

Best Alternatives
Context / RAM
Downloads
Likes
...ixtral 8x22B Instruct V0.1 FP864K / 140.9 GB980
Llama 3 IMPACTS 2x8B 64K MLX64K / 27.4 GB435
Dolphin 2.6 Mixtral 8x7b32K / 93.6 GB11285211
Dolphin 2.6 Mixtral 8x7b32K / 93.6 GB7806217
...eqlen 4096 Bs 4 Optimum 0 0 2332K /  GB80
...eqlen 4096 Bs 4 Optimum 0 0 2332K /  GB91
Dolphin 2.7 Mixtral 8x7b32K / 93.6 GB2178170
Empower Functions Medium32K / 93.6 GB171
Mixtral 8x7B Instruct V0.132K /  GB50
...ral 8x7b Instruct V0.1 Int4 Ov32K / 0 GB164
Note: green Score (e.g. "73.2") means that the model is better than Severian/Nexus-4x7B-IKM-MLX.