LLM EXPLORER 61,491 MODELS INDEXED

Luminex 34B V0.1 EXL2 8.0bpw by KnutJaegersberg

By KnutJaegersberg · 1 downloads
HF Repo ↗ Copy URL

Luminex 34B V0.1 EXL2 8.0bpw is an open-source language model by KnutJaegersberg. Features: 34b LLM, VRAM: 34.9GB, Context: 32K, License: other, Quantized, LLM Explorer Score: 0.12.

Base model:finetune:jondurbin/... Base model:jondurbin/bagel-34b...   Conversational   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/KnutJaegersberg/Luminex-34B-v0.1-exl2-8.0bpw 

Luminex 34B V0.1 EXL2 8.0bpw Parameters and Internals

Additional Notes 
This model is [SimpleSmaug-34b](https://huggingface.co/fblgit/UNA-SimpleSmaug-34b-v1beta) with LaserRMT applied.
LLM NameLuminex 34B V0.1 EXL2 8.0bpw
Repository 🤗https://huggingface.co/KnutJaegersberg/Luminex-34B-v0.1-exl2-8.0bpw 
Base Model(s)  jondurbin/bagel-34b-v0.2   jondurbin/bagel-34b-v0.2
Model Size34b
Required VRAM34.9 GB
Updated2026-07-25
MaintainerKnutJaegersberg
Model Typellama
Model Files  8.5 GB: 1-of-5   8.6 GB: 2-of-5   8.5 GB: 3-of-5   8.6 GB: 4-of-5   0.7 GB: 5-of-5
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Luminex 34B V0.1 EXL2 8.0bpw

Best Alternatives
Context / RAM
Downloads
Likes
...34B 200K Aezakmi Raw 1902 EXL2195K / 20.7 GB31
Yi 34B 200K MAR2024 EXL2 4bpw195K / 18 GB41
...B 200K RPMerge 4.65bpw H6 EXL2195K / 10.5 GB82
...mi Raw Toxic 2702 4.65bpw EXL2195K / 20.8 GB72
Yi 34B 200K RPMerge195K / 68.9 GB7260
Opus V1 34B 5.0bpw H6 EXL2195K / 22.3 GB52
Opus V1 34B 8.0bpw H8 EXL2195K / 34.8 GB71
Opus V1 34B 4.0bpw H6 EXL2195K / 18 GB51
34B Beta 5.0bpw H6 EXL2195K / 22.3 GB41
34B Beta 4.0bpw H6 EXL2195K / 18.1 GB21
Note: green Score (e.g. "73.2") means that the model is better than KnutJaegersberg/Luminex-34B-v0.1-exl2-8.0bpw.