SakaMoe 3x1.6B Instruct is an open-source language model by Sakalti. Features: 1.6b LLM, VRAM: 3.1GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.18.
Arxiv:1910.09700 Autotrain compatible Base model:finetune:sakalti/sj... Base model:sakalti/sjt-0.5b Conversational En Endpoints compatible Instruct Ja Moe Qwen2 moe Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/SakaMoe-3x1.6B-Instruct
SakaMoe 3x1.6B Instruct Benchmarks
MMLU Pro: 9.81
GPQA: 2.24
MUSR: 0.94
BBH: 7.53
IFEval: 23.71 vs 88 (so35)-73.1%
MATH Lvl 5: 5.44
LLME Score: 0.1786
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
SakaMoe 3x1.6B Instruct Parameters and Internals
| LLM Name | SakaMoe 3x1.6B Instruct |
| Repository 🤗 | https://huggingface.co/Sakalti/SakaMoe-3x1.6B-Instruct |
| Base Model(s) | |
| Model Size | 1.6b |
| Required VRAM | 3.1 GB |
| Updated | 2025-09-14 |
| Maintainer | Sakalti |
| Model Type | qwen2_moe |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en ja |
| Model Architecture | Qwen2MoeForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Rank the SakaMoe 3x1.6B Instruct 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! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a