LLM EXPLORER 67,181 MODELS INDEXED

MP 02 16B Preview by Manprot

By Manprot · 91 downloads
HF Repo ↗ Copy URL

MP 02 16B Preview is an open-source language model by Manprot. Features: 16b LLM, VRAM: 24GB, License: mit, Quantized, LLM Explorer Score: 0.45, ELO: 1475.

Base model:finetune:zai-org/gl... Base model:zai-org/glm-5.3-fla...   Conversational Dataset:anthracite-org/c2 logs... Dataset:best-distill/glm-5.3-f... Dataset:closestfriend/glm-5.3-... Dataset:flaviojoshua/glm53-fla... Dataset:franckabgrall/glm53-fl... Dataset:gryphe/sonnet3.5-charc... Dataset:kaivoss/ultradata-sft-... Dataset:liangzhidanta/claude-c... Dataset:liangzhidanta/claude-c... Dataset:offlin33er/glm-5.3-fla... Dataset:open-athena/glm-5.3-rl... Dataset:open-athena/glm-5.3-tm... Dataset:rallex3/glm-5.3-flash-... Dataset:shanjiaz/glm-5.3-flash... Dataset:sollamon/ox-alpha-glm-... Dataset:zek-takai/glm53-flash-...   En   Endpoints compatible   Expert-pruning   Gguf   Glm   Glm5 next   Image-text-to-text   Moe   Preview   Q4   Quantized   Reap   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Manprot/MP-02-16B-Preview 

MP 02 16B Preview Benchmarks

LMSys ELO 1475 vs 1272 (so35) 16%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

MP 02 16B Preview Parameters and Internals

LLM NameMP 02 16B Preview
Repository 🤗https://huggingface.co/Manprot/MP-02-16B-Preview 
Base Model(s)  zai-org/GLM-5.3-Flash   zai-org/GLM-5.3-Flash
Model Size16b
Required VRAM24 GB
Updated2026-11-11
MaintainerManprot
Model Typeglm5_next
Model Files  12.9 GB   1.2 GB   2.7 GB: 1-of-62   1.6 GB: 2-of-62   0.2 GB: 3-of-62   0.7 GB: 4-of-62   0.7 GB: 5-of-62   0.4 GB: 6-of-62   0.3 GB: 7-of-62   0.7 GB: 8-of-62   0.4 GB: 9-of-62   0.3 GB: 10-of-62   1.1 GB: 11-of-62   0.3 GB: 12-of-62   0.4 GB: 13-of-62   0.3 GB: 14-of-62   1.1 GB: 15-of-62   0.0 GB: 16-of-62   0.9 GB: 17-of-62   0.7 GB: 18-of-62   0.7 GB: 19-of-62   0.0 GB: 20-of-62   0.7 GB: 21-of-62   0.7 GB: 22-of-62   0.4 GB: 23-of-62   0.3 GB: 24-of-62   0.7 GB: 25-of-62   0.7 GB: 26-of-62   0.0 GB: 27-of-62   0.7 GB: 28-of-62   0.7 GB: 29-of-62   0.4 GB: 30-of-62   0.3 GB: 31-of-62   1.1 GB: 32-of-62   0.3 GB: 33-of-62   0.0 GB: 34-of-62   0.7 GB: 35-of-62   0.7 GB: 36-of-62   0.4 GB: 37-of-62   0.7 GB: 38-of-62   0.3 GB: 39-of-62   0.7 GB: 40-of-62
Supported Languagesen
GGUF QuantizationYes
Quantization Typeq4|gguf|q4_k
Model ArchitectureGlm5NextForConditionalGeneration
Licensemit
Transformers Version5.16.0