LLM EXPLORER 59,420 MODELS INDEXED

Mirai 70B 1.0 by Blackroot

By Blackroot · 10 downloads
HF Repo ↗ Copy URL

Mirai 70B 1.0 is an open-source language model by Blackroot. Features: 70b LLM, VRAM: 141.9GB, Context: 128K, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.16.

  Merged Model   Arxiv:2403.19522 Base model:allenai/llama-3.1-t... Base model:bllossom/llama-3-ko... Base model:hitachi-nlp/llama-3... Base model:meta-llama/meta-lla... Base model:pku-baichuan-mlsyst... Base model:sao10k/l3.1-70b-eur... Base model:tokyotech-llm/llama... Base model:tsinghuac3i/llama-3... Base model:whiterabbitneo/llam... Base model:yentinglin/llama-3-...   Experimental   Fp16   Indie   Instruct   Llama   Quantized   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Blackroot/Mirai-70B-1.0 

Mirai 70B 1.0 Parameters and Internals

LLM NameMirai 70B 1.0
Repository 🤗https://huggingface.co/Blackroot/Mirai-70B-1.0 
Base Model(s)  huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated   Sao10K/L3.1-70B-Euryale-v2.2   rinna/llama-3-youko-70B   Llama 3 Taiwan 70B Instruct   Meta Llama 3 70B   PKU-Baichuan-MLSystemLab/Llama3-PBM-Nova-70B   tokyotech-llm/Llama-3.1-Swallow-70B-v0.1   Llama 3 Korean Bllossom 70B   WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-70B   Llama 3 70B UltraMedical   allenai/Llama-3.1-Tulu-3-70B   hitachi-nlp/Llama-3.1-70B-FLDx2   huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated   Sao10K/L3.1-70B-Euryale-v2.2   rinna/llama-3-youko-70B   yentinglin/Llama-3-Taiwan-70B-Instruct   meta-llama/Meta-Llama-3-70B   PKU-Baichuan-MLSystemLab/Llama3-PBM-Nova-70B   tokyotech-llm/Llama-3.1-Swallow-70B-v0.1   Bllossom/llama-3-Korean-Bllossom-70B   WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-70B   TsinghuaC3I/Llama-3-70B-UltraMedical   allenai/Llama-3.1-Tulu-3-70B   hitachi-nlp/Llama-3.1-70B-FLDx2
Merged ModelYes
Model Size70b
Required VRAM141.9 GB
Updated2026-08-25
MaintainerBlackroot
Model Typellama
Instruction-BasedYes
Model Files  4.7 GB: 1-of-30   4.7 GB: 2-of-30   5.0 GB: 3-of-30   5.0 GB: 4-of-30   4.7 GB: 5-of-30   4.7 GB: 6-of-30   4.7 GB: 7-of-30   5.0 GB: 8-of-30   5.0 GB: 9-of-30   4.7 GB: 10-of-30   4.7 GB: 11-of-30   4.7 GB: 12-of-30   5.0 GB: 13-of-30   5.0 GB: 14-of-30   4.7 GB: 15-of-30   4.7 GB: 16-of-30   4.7 GB: 17-of-30   5.0 GB: 18-of-30   5.0 GB: 19-of-30   4.7 GB: 20-of-30   4.7 GB: 21-of-30   4.7 GB: 22-of-30   5.0 GB: 23-of-30   5.0 GB: 24-of-30   4.7 GB: 25-of-30   4.7 GB: 26-of-30   4.7 GB: 27-of-30   5.0 GB: 28-of-30   5.0 GB: 29-of-30   2.0 GB: 30-of-30
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.46.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Mirai 70B 1.0

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB415
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB253
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB252
...0B Instruct Gradient 262K 4bit256K / 39.7 GB253
...0B Instruct Gradient 262K 8bit256K / 75 GB262
...0B Instruct Gradient 262K 2bit256K / 21.9 GB201
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB71
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB60
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60