LLM EXPLORER 66,704 MODELS INDEXED

Umochi 60K WSP by Techions

By Techions · 268 downloads
HF Repo ↗ Copy URL

Umochi 60K WSP is an open-source language model by Techions. Features: 32b LLM, License: apache-2.0, Quantized, Instruction-Based, Code Generating, ELO: 1232, HumanEval: 83.2.

Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-...   Code   Codegen   Coding-assistant   En   Gguf   Instruct   Java   Netty   Project-loom   Quantized   Region:us   Spring-boot   Threejs   Umochi   Virtual-threads   Webgpu   Weight-space-programming   Zh
Model Card on HF 🤗: https://huggingface.co/Techions/Umochi-60K-WSP 

Umochi 60K WSP Benchmarks

LMSys ELO 1232 vs 1272 (so35) -3.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Umochi 60K WSP Parameters and Internals

LLM NameUmochi 60K WSP
Repository 🤗https://huggingface.co/Techions/Umochi-60K-WSP 
Model NameUmochi-60K-WSP
Base Model(s)  Qwen/Qwen2.5-Coder-32B-Instruct   Qwen/Qwen2.5-Coder-32B-Instruct
Model Size32b
Required VRAM0 GB
Updated2026-11-05
MaintainerTechions
Model Typeumochi
Instruction-BasedYes
Model Files  0.0 GB   0.0 GB
Supported Languagesen zh
GGUF QuantizationYes
Quantization Typegguf
Generates CodeYes
Model ArchitectureQwen2MoeForCausalLM
Licenseapache-2.0