Kimi K2 Instruct 0905 BF16 by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  Kimi K2 Instruct 0905 BF16   URL Share it on

  Autotrain compatible Base model:finetune:moonshotai... Base model:moonshotai/kimi-k2-...   Conversational   Custom code   Deepseek v3   Endpoints compatible   Instruct   Region:us   Safetensors   Sharded   Tensorflow   Unsloth

Kimi K2 Instruct 0905 BF16 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kimi K2 Instruct 0905 BF16 (unsloth/Kimi-K2-Instruct-0905-BF16)
๐ŸŒŸ Advertise your project ๐Ÿš€

Kimi K2 Instruct 0905 BF16 Parameters and Internals

LLM NameKimi K2 Instruct 0905 BF16
Repository ๐Ÿค—https://huggingface.co/unsloth/Kimi-K2-Instruct-0905-BF16 
Base Model(s)  Kimi K2 Instruct 0905   moonshotai/Kimi-K2-Instruct-0905
Model Size1026.4b
Required VRAM1399.1 GB
Updated2025-09-08
Maintainerunsloth
Model Typedeepseek_v3
Instruction-BasedYes
Model Files  1.0 GB: 1-of-62   34.1 GB: 2-of-62   34.1 GB: 3-of-62   34.1 GB: 4-of-62   34.1 GB: 5-of-62   34.1 GB: 6-of-62   34.1 GB: 7-of-62   34.1 GB: 8-of-62   34.1 GB: 9-of-62   34.1 GB: 10-of-62   34.1 GB: 11-of-62   34.1 GB: 12-of-62   34.1 GB: 13-of-62   34.1 GB: 14-of-62   34.1 GB: 15-of-62   34.1 GB: 16-of-62   34.1 GB: 17-of-62   34.1 GB: 18-of-62   34.1 GB: 19-of-62   34.1 GB: 20-of-62   34.1 GB: 21-of-62   34.1 GB: 22-of-62   34.1 GB: 23-of-62   34.1 GB: 24-of-62   34.1 GB: 25-of-62   34.1 GB: 26-of-62   34.1 GB: 27-of-62   34.1 GB: 28-of-62   34.1 GB: 29-of-62   34.1 GB: 30-of-62   34.1 GB: 31-of-62   34.1 GB: 32-of-62   34.1 GB: 33-of-62   34.1 GB: 34-of-62   34.1 GB: 35-of-62   34.1 GB: 36-of-62   34.1 GB: 37-of-62   34.1 GB: 38-of-62   34.1 GB: 39-of-62   34.1 GB: 40-of-62   34.1 GB: 41-of-62   34.1 GB: 42-of-62
Model ArchitectureDeepseekV3ForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.56.1
Vocabulary Size163840

Best Alternatives to Kimi K2 Instruct 0905 BF16

Best Alternatives
Context / RAM
Downloads
Likes
...i K2 Instruct 0905 Mlx DQ3 K M256K / 207.8 GB1334
Kimi K2 Instruct BF16128K / 1367.3 GB3843
Kimi K2 Instruct 4bit128K / 143.2 GB29909
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Kimi-K2-Instruct-0905-BF16.

Rank the Kimi K2 Instruct 0905 BF16 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51191 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124