LLM EXPLORER 60,783 MODELS INDEXED

Merge Mixtral Prometheus 8x7B by vicgalle

By vicgalle · 12 downloads
HF Repo ↗ Copy URL

Merge Mixtral Prometheus 8x7B is an open-source language model by vicgalle. Features: 46.7b LLM, VRAM: 91.9GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, Merged, LLM Explorer Score: 0.19.

  Merged Model   Arxiv:2406.07188 Base model:mistralai/mixtral-8... Base model:prometheus-eval/pro...   Conversational   Endpoints compatible   Instruct Mistralai/mixtral-8x7b-instruc...   Mixtral   Model-index   Moe Prometheus-eval/prometheus-8x7...   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/vicgalle/Merge-Mixtral-Prometheus-8x7B 

Merge Mixtral Prometheus 8x7B Parameters and Internals

Model Type 
text-generation
Additional Notes 
Merge-Mixtral-Prometheus-8x7B is a merge of two models using LazyMergekit: prometheus-eval/prometheus-8x7b-v2.0 and mistralai/Mixtral-8x7B-Instruct-v0.1
LLM NameMerge Mixtral Prometheus 8x7B
Repository 🤗https://huggingface.co/vicgalle/Merge-Mixtral-Prometheus-8x7B 
Base Model(s)  prometheus-eval/prometheus-8x7b-v2.0   mistralai/Mixtral-8x7B-Instruct-v0.1   prometheus-eval/prometheus-8x7b-v2.0   mistralai/Mixtral-8x7B-Instruct-v0.1
Merged ModelYes
Model Size46.7b
Required VRAM91.9 GB
Updated2026-07-27
Maintainervicgalle
Model Typemixtral
Instruction-BasedYes
Model Files  1.9 GB: 1-of-48   2.0 GB: 2-of-48   2.0 GB: 3-of-48   2.0 GB: 4-of-48   2.0 GB: 5-of-48   2.0 GB: 6-of-48   2.0 GB: 7-of-48   2.0 GB: 8-of-48   2.0 GB: 9-of-48   2.0 GB: 10-of-48   2.0 GB: 11-of-48   2.0 GB: 12-of-48   2.0 GB: 13-of-48   2.0 GB: 14-of-48   2.0 GB: 15-of-48   2.0 GB: 16-of-48   2.0 GB: 17-of-48   2.0 GB: 18-of-48   2.0 GB: 19-of-48   2.0 GB: 20-of-48   2.0 GB: 21-of-48   2.0 GB: 22-of-48   2.0 GB: 23-of-48   2.0 GB: 24-of-48   2.0 GB: 25-of-48   2.0 GB: 26-of-48   2.0 GB: 27-of-48   2.0 GB: 28-of-48   2.0 GB: 29-of-48   2.0 GB: 30-of-48   2.0 GB: 31-of-48   2.0 GB: 32-of-48   2.0 GB: 33-of-48   2.0 GB: 34-of-48   2.0 GB: 35-of-48   2.0 GB: 36-of-48   2.0 GB: 37-of-48   2.0 GB: 38-of-48   2.0 GB: 39-of-48   2.0 GB: 40-of-48   2.0 GB: 41-of-48   2.0 GB: 42-of-48   2.0 GB: 43-of-48   2.0 GB: 44-of-48   2.0 GB: 45-of-48   2.0 GB: 46-of-48
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Merge Mixtral Prometheus 8x7B

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB8428934720
Mixtral 8x7B Instruct V0.132K / 93.6 GB70
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB33830
...xtral 8x7B Yes Instruct LimaRP32K / 93.5 GB51
Notux 8x7b V132K / 93.6 GB43165
BagelMIsteryTour V2 8x7B32K / 93.5 GB9417
...rkrautLM Mixtral 8x7B Instruct32K / 93.6 GB8422
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB3740
Sage Ft Mixtral 8x7b32K / 90 GB4525
Dolphin 2.5 Mixtral 8x7b32K / 93.6 GB41251235
Note: green Score (e.g. "73.2") means that the model is better than vicgalle/Merge-Mixtral-Prometheus-8x7B.