AI Model Catalogue

ministral-3:8b — available to run locally via Ollama on CPU and GPU hardware.

Qwen2.5-7B-Instruct-AWQ

Open-source Qwen2.5-7B-Instruct-AWQ model from qwen — available for download and self-hosting on Hugging Face.

OTel-LLM-8.3B-IT

farbodtavakkoli

Open-source OTel-LLM-8.3B-IT model from farbodtavakkoli — available for download and self-hosting on Hugging Face.

Qwen3-VL-30B-A3B-Instruct-AWQ

quanttrio

Open-source Qwen3-VL-30B-A3B-Instruct-AWQ model from quanttrio — available for download and self-hosting on Hugging Face.

Mistral-7B-v0.1

mistralai

Open-source Mistral-7B-v0.1 model from mistralai — available for download and self-hosting on Hugging Face.

deepseek-v3.1:671b

deepseek-v3.1:671b — available to run locally via Ollama on CPU and GPU hardware.

kimi-k2.5

kimi-k2.5 — available to run locally via Ollama on CPU and GPU hardware.

gemma3:12b

gemma3:12b — available to run locally via Ollama on CPU and GPU hardware.

qwen3-vl:235b-instruct

qwen3-vl:235b-instruct — available to run locally via Ollama on CPU and GPU hardware.

ministral-3:3b

ministral-3:3b — available to run locally via Ollama on CPU and GPU hardware.

ministral-3:14b

ministral-3:14b — available to run locally via Ollama on CPU and GPU hardware.

gpt-oss:20b

gpt-oss:20b — available to run locally via Ollama on CPU and GPU hardware.

gemma3:4b

gemma3:4b — available to run locally via Ollama on CPU and GPU hardware.

kimi-k2:1t

kimi-k2:1t — available to run locally via Ollama on CPU and GPU hardware.

mistral-large-3:675b

mistral-large-3:675b — available to run locally via Ollama on CPU and GPU hardware.

Llama-3.2-1B

meta-llama

Open-source Llama-3.2-1B model from meta-llama — available for download and self-hosting on Hugging Face.

Qwen2.5-14B-Instruct-AWQ

Open-source Qwen2.5-14B-Instruct-AWQ model from qwen — available for download and self-hosting on Hugging Face.

Qwen2.5-0.5B

Open-source Qwen2.5-0.5B model from qwen — available for download and self-hosting on Hugging Face.

Qwen2.5-14B-Instruct

Open-source Qwen2.5-14B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Qwen3-14B-AWQ

Open-source Qwen3-14B-AWQ model from qwen — available for download and self-hosting on Hugging Face.

Llama-3.2-1B-Instruct-FP8-dynamic

redhatai

Open-source Llama-3.2-1B-Instruct-FP8-dynamic model from redhatai — available for download and self-hosting on Hugging Face.

OpenELM-1_1B-Instruct

apple

Open-source OpenELM-1_1B-Instruct model from apple — available for download and self-hosting on Hugging Face.

Qwen2.5-1.5B

Open-source Qwen2.5-1.5B model from qwen — available for download and self-hosting on Hugging Face.

Llama-3.2-3B

meta-llama

Open-source Llama-3.2-3B model from meta-llama — available for download and self-hosting on Hugging Face.

glm-5.1

glm-5.1 — available to run locally via Ollama on CPU and GPU hardware.

gpt-oss:120b

gpt-oss:120b — available to run locally via Ollama on CPU and GPU hardware.

rnj-1:8b

rnj-1:8b — available to run locally via Ollama on CPU and GPU hardware.

Qwen2.5-Coder-7B-Instruct

Open-source Qwen2.5-Coder-7B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

textcodeinstruct

minimax-m2.1

minimax-m2.1 — available to run locally via Ollama on CPU and GPU hardware.

Qwen2.5-Coder-7B

Open-source Qwen2.5-Coder-7B model from qwen — available for download and self-hosting on Hugging Face.

textcodefree

minimax-m2.5

minimax-m2.5 — available to run locally via Ollama on CPU and GPU hardware.

gemma3:27b

gemma3:27b — available to run locally via Ollama on CPU and GPU hardware.

qwen3.5:397b

qwen3.5:397b — available to run locally via Ollama on CPU and GPU hardware.

glm-4.7

glm-4.7 — available to run locally via Ollama on CPU and GPU hardware.

Qwen2.5-32B-Instruct-AWQ

Open-source Qwen2.5-32B-Instruct-AWQ model from qwen — available for download and self-hosting on Hugging Face.

nemotron-3-super

nemotron-3-super — available to run locally via Ollama on CPU and GPU hardware.