LLM EXPLORER 60,828 MODELS INDEXED

MetaMath Mistral Pro by TencentARC

By TencentARC · 18 downloads

MetaMath Mistral Pro is an open-source language model by TencentARC. Features: 9b LLM, VRAM: 17.9GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.14.

  Arxiv:2401.02415   Dataset:meta-math/metamathqa   En   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow

MetaMath Mistral Pro Parameters and Internals

Supported Languages 
en (English)
Input Output 
Input Format:
<|user|> Your message here! <|assistant|>
Performance Tips:
Make sure to include a newline after <|assistant|>, this can affect generation quality quite a bit.
LLM NameMetaMath Mistral Pro
Repository πŸ€—https://huggingface.co/TencentARC/MetaMath-Mistral-Pro 
Model Size9b
Required VRAM17.9 GB
Updated2026-08-08
MaintainerTencentARC
Model Typemistral
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   3.1 GB: 4-of-4
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to MetaMath Mistral Pro

Best Alternatives
Context / RAM
Downloads
Likes
Peagle 9B32K / 18 GB128140
Peagle 9B32K / 18 GB82030
...onarch Neurotic 9B Passthrough32K / 17.9 GB820
Mistral 9B Instruct32K / 35.9 GB70
GML Mistral Merged V132K / 18 GB861
Garbage 9B32K / 17.9 GB723
Bepis 9B32K / 18 GB1006
Mistral 9B Instruct V0.232K / 17.9 GB893
Notus TheTop 7B Passthrough32K / 18 GB50
...raAI Foredoomed 9B EXL 2.8 Bpw32K / 3.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than TencentARC/MetaMath-Mistral-Pro.