LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Karakuri Lm 8x7b Instruct V0.1 by karakuri-ai

 »  All LLMs  »  karakuri-ai  »  Karakuri Lm 8x7b Instruct V0.1   URL Share it on

  12   

Karakuri Lm 8x7b Instruct V0.1 is an open-source language model by karakuri-ai. Features: 46.7b LLM, VRAM: 93.6GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.16.

Base model:finetune:tokyotech-... Base model:tokyotech-llm/swall...   Conversational Dataset:databricks/databricks-... Dataset:glaiveai/glaive-code-a... Dataset:glaiveai/glaive-functi... Dataset:gretelai/synthetic tex...   Dataset:meta-math/metamathqa Dataset:microsoft/orca-math-wo... Dataset:neural-bridge/rag-data... Dataset:neural-bridge/rag-hall...   Dataset:nvidia/helpsteer   Dataset:openassistant/oasst2   Deploy:azure   En   Endpoints compatible   Instruct   Ja   Mixtral   Moe   Region:us   Safetensors   Sharded   Steerlm   Tensorflow
Model Card on HF 🤗: https://huggingface.co/karakuri-ai/karakuri-lm-8x7b-instruct-v0.1 

Karakuri Lm 8x7b Instruct V0.1 Benchmarks

LLME Score: 0.16026
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Karakuri Lm 8x7b Instruct V0.1 (karakuri-ai/karakuri-lm-8x7b-instruct-v0.1)
🌟 Advertise your project 🚀

Karakuri Lm 8x7b Instruct V0.1 Parameters and Internals

Model Type 
Mixture of Experts (MoE)
Additional Notes 
The model sometimes attempts to call unprovided tools. Implement a post-process to exclude those tools.
Supported Languages 
en (primary), ja (primary)
Training Details 
Data Sources:
databricks/databricks-dolly-15k, glaiveai/glaive-code-assistant-v3, glaiveai/glaive-function-calling-v2, gretelai/synthetic_text_to_sql, meta-math/MetaMathQA, microsoft/orca-math-word-problems-200k, neural-bridge/rag-dataset-12000, neural-bridge/rag-hallucination-dataset-1000, nvidia/HelpSteer, OpenAssistant/oasst2, KARAKURI Instruction Dataset, KARAKURI Corpus
Data Volume:
1 billion tokens
Hardware Used:
8 nodes of an Amazon EC2 trn1.32xlarge instance
LLM NameKarakuri Lm 8x7b Instruct V0.1
Repository 🤗https://huggingface.co/karakuri-ai/karakuri-lm-8x7b-instruct-v0.1 
Base Model(s)  tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1   tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1
Model Size46.7b
Required VRAM93.6 GB
Updated2026-04-01
Maintainerkarakuri-ai
Model Typemixtral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-19   5.0 GB: 2-of-19   5.0 GB: 3-of-19   4.9 GB: 4-of-19   5.0 GB: 5-of-19   5.0 GB: 6-of-19   4.9 GB: 7-of-19   5.0 GB: 8-of-19   5.0 GB: 9-of-19   4.9 GB: 10-of-19   5.0 GB: 11-of-19   5.0 GB: 12-of-19   5.0 GB: 13-of-19   4.9 GB: 14-of-19   5.0 GB: 15-of-19   5.0 GB: 16-of-19   4.9 GB: 17-of-19   5.0 GB: 18-of-19   4.2 GB: 19-of-19
Supported Languagesen ja
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32128
Torch Data Typebfloat16

Best Alternatives to Karakuri Lm 8x7b Instruct V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB4629634650
...xtral 8x7B Yes Instruct LimaRP32K / 93.5 GB61
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB12990
Merge Mixtral Prometheus 8x7B32K / 91.9 GB172
...rkrautLM Mixtral 8x7B Instruct32K / 93.6 GB123322
Notux 8x7b V132K / 93.6 GB29164
BagelMIsteryTour V2 8x7B32K / 93.5 GB11317
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB3740
Dolphin 2.5 Mixtral 8x7b32K / 93.6 GB41251235
Sage Ft Mixtral 8x7b32K / 90 GB1324
Note: green Score (e.g. "73.2") means that the model is better than karakuri-ai/karakuri-lm-8x7b-instruct-v0.1.

Rank the Karakuri Lm 8x7b Instruct V0.1 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52394 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer