LLM EXPLORER 66,383 MODELS INDEXED

Mpt 7B GGML by rustformers

By rustformers · 21 downloads
HF Repo ↗ Copy URL

Mpt 7B GGML is an open-source language model by rustformers. Features: 7b LLM, VRAM: 3.7GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.07.

  Dataset:allenai/s2orc   Dataset:bigcode/the-stack   Dataset:c4   Dataset:mc4 Dataset:togethercomputer/redpa...   En   Ggml   Instruct   Llm-rs   Mpt   Q4   Q4 0   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/rustformers/mpt-7b-ggml 

Mpt 7B GGML Parameters and Internals

Model Type 
text generation
Supported Languages 
en (English text and code)
Training Details 
Data Sources:
mc4, c4, togethercomputer/RedPajama-Data-1T, bigcode/the-stack, allenai/s2orc
Data Volume:
1T tokens
Methodology:
modified transformer architecture optimized for efficient training and inference
Model Architecture:
decoder-style transformer
LLM NameMpt 7B GGML
Repository 🤗https://huggingface.co/rustformers/mpt-7b-ggml 
Model Size7b
Required VRAM3.7 GB
Updated2026-06-22
Maintainerrustformers
Model Typempt
Instruction-BasedYes
Model Files  13.3 GB   3.7 GB   3.7 GB   5.0 GB   5.0 GB   13.3 GB   13.3 GB   3.7 GB   3.7 GB   5.0 GB   5.0 GB   3.7 GB   3.7 GB   5.0 GB   5.0 GB   13.3 GB   3.7 GB   3.7 GB   5.0 GB   5.0 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml|q4|q4_0|q5_1
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Mpt 7B GGML

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 7B Instruct GGML0K / 3 GB1020
Llama 2 7B 32K Instruct GGML0K / 2.9 GB78
Vigogne 2 7B Instruct GGML0K / 2.9 GB42
Falcon 7B Instruct GGML0K / 4.1 GB1240
Redpajama 7B GGML0K / 3.9 GB93
MPT 7B Instruct GGML0K / 3.7 GB6430
Badqubits Mistral 7B V03 Ft0K / 0.2 GB281
Poetes Mistral 7B Lora0K / 0.2 GB251
Qwen Phoenix Lora0K / 0.2 GB171
Forma Uiux Auditor0K / 0.2 GB251
Note: green Score (e.g. "73.2") means that the model is better than rustformers/mpt-7b-ggml.