What are the hardware requirements for Poro 34B GGUF?

Poro 34B GGUF requires approximately 14.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Poro 34B GGUF and how large is it?

Poro 34B GGUF is developed by TheBloke, a model with 34b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Poro 34B GGUF?

Poro 34B GGUF is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Poro 34B GGUF by TheBloke — VRAM 14.5GB

Name: Poro 34B GGUF
Author: TheBloke

Poro 34B GGUF is an open-source language model by TheBloke. Features: 34b LLM, VRAM: 14.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.1.

Base model:lumiopen/poro-34b Base model:quantized:lumiopen/... Bloom Dataset:allenai/dolma Dataset:bigcode/starcoderdata Dataset:cerebras/slimpajama-62... Dataset:mc4 Gguf Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/TheBloke/Poro-34B-GGUF

Poro 34B GGUF Parameters and Internals

Model Type

bloom, decoder-only transformer

Use Cases

Areas:

Research, Testing

Limitations:

Requires further fine-tuning for most use cases, Limited to Finnish, English, and code proficiency

Additional Notes

Poro is part of an ongoing effort to support non-English and low resource languages.

Supported Languages

Finnish (Fluent), English (Fluent), Code (Fluent)

Training Details

Data Sources:

cerebras/SlimPajama-627B, bigcode/starcoderdata, mc4, allenai/dolma

Data Volume:

1 trillion tokens (500 billion as of this release)

Methodology:

Pretrained using BLOOM architecture with ALiBi embeddings

Context Length:

2048

Hardware Used:

512 AMD MI250X GPUs

Model Architecture:

Generative pretrained transformer with BLOOM architecture and ALiBi embeddings

Responsible Ai Considerations

Fairness:

Poro is a release of a partially trained model; outputs might reflect biases of training data.

Transparency:

Efforts towards creating open-source models for Finnish and English with code.

Accountability:

Joint collaboration by multiple parties, including LumiOpen and academic institutions.

Mitigation Strategies:

Further tuning recommended for most use cases.

LLM Name	Poro 34B GGUF
Repository 🤗	https://huggingface.co/TheBloke/Poro-34B-GGUF
Model Name	Poro 34B
Model Creator	LumiOpen
Base Model(s)	Poro 34B LumiOpen/Poro-34B
Model Size	34b
Required VRAM	14.5 GB
Updated	2026-08-07
Maintainer	TheBloke
Model Type	bloom
Model Files	14.5 GB 20.2 GB 18.5 GB 15.5 GB 20.0 GB 22.4 GB 20.1 GB 24.3 GB 26.1 GB 24.3 GB 28.8 GB 37.3 GB
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	AutoModel
License	apache-2.0

Rank the Poro 34B GGUF capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Poro 34B GGUF

Best Alternatives	Context / RAM	Downloads	Likes
Mergekit Slerp Fecxcxs GGUF	0K / 8.4 GB	8	0
...gekit Passthrough Zpfenfn GGUF	0K / 8.7 GB	11	0
...4B 200K DARE Megamerge V8 GGUF	0K / 9.3 GB	3504	14
Yi 1.5 34B Chat GGUF	0K / 12.8 GB	49	5
...ous Capybara Limarpv3 34B GGUF	0K / 14.6 GB	1038	29
Nous Hermes 2 Yi 34B GGUF	0K / 14.6 GB	1336	40
...y 34B 200K Chat Evaluator GGUF	0K / 12.8 GB	1054	11
34B Beta GGUF	0K / 12.8 GB	146	4
StructLM 34B GGUF	0K / 12.5 GB	196	2
CodeLlama 34B Python Hf GGUF	0K / 12.5 GB	514	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Poro-34B-GGUF.