Models¶

See available models in Dria Network below:

Available Models¶

Enum	Serialized Name	Description
`NousTheta`	`finalend/hermes-3-llama-3.1:8b-q8_0`	Nous's Hermes-2-Theta model, q8_0 quantized
`Phi3Medium`	`phi3:14b-medium-4k-instruct-q4_1`	Microsoft's Phi3 Medium model, q4_1 quantized
`Phi3Medium128k`	`phi3:14b-medium-128k-instruct-q4_1`	Microsoft's Phi3 Medium model, 128k context length, q4_1 quantized
`Phi3_5Mini`	`phi3.5:3.8b`	Microsoft's Phi3.5 Mini model, 3.8b parameters
`Phi3_5MiniFp16`	`phi3.5:3.8b-mini-instruct-fp16`	Microsoft's Phi3.5 Mini model, 3.8b parameters
`Gemma2_9B`	`gemma2:9b-instruct-q8_0`	Google's Gemma2 model, 9B parameters
`Gemma2_9BFp16`	`gemma2:9b-instruct-fp16`	Google's Gemma2 model, 9B parameters, fp16
`Llama3_1_8B`	`llama3.1:latest`	Meta's Llama3.1 model, 8B parameters
`Llama3_1_8Bq8`	`llama3.1:8b-instruct-q8_0`	Meta's Llama3.1 model q8
`Llama3_1_8Bf16`	`llama3.1:8b-instruct-fp16`	Meta's Llama3.1 model fp16
`Llama3_1_8BTextQ4KM`	`llama3.1:8b-text-q4_K_M`	Meta's Llama3.1 model q4
`Llama3_1_8BTextQ8`	`llama3.1:8b-text-q8_0`	Meta's Llama3.1 model q8
`Llama3_1_70B`	`llama3.1:70b-instruct-q4_0`	Meta's Llama3.1 model, 70B parameters
`Llama3_1_70Bq8`	`llama3.1:70b-instruct-q8_0`	Meta's Llama3.1 model q8
`Llama3_1_70BTextQ4KM`	`llama3.1:70b-text-q4_0`	Meta's LLama3.1 model fp16
`Llama3_2_1B`	`llama3.2:1b`	Meta's LLama3.2 Edge models, 1B parameters
`Llama3_2_3B`	`llama3.2:3b`	Meta's LLama3.2 Edge models, 3B parameters
`Llama3_3_70B`	`llama3.3:70b`	Meta's LLama3.3 Edge models, 3B parameters
`Llama3_2_1BTextQ4KM`	`llama3.2:1b-text-q4_K_M`	Meta's LLama3.2 Edge models, 1B parameters, q4
`Qwen2_5_7B`	`qwen2.5:7b-instruct-q5_0`	Alibaba's Qwen2.5 model, 7B parameters
`Qwen2_5_7Bf16`	`qwen2.5:7b-instruct-fp16`	Alibaba's Qwen2.5 model, 7B parameters, fp16
`Qwen2_5_32Bf16`	`qwen2.5:32b-instruct-fp16`	Alibaba's Qwen2.5 model, 32B parameters, fp16
`Qwen2_5Coder1_5B`	`qwen2.5-coder:1.5b`	Alibaba's Qwen2.5 Coder
`Qwen2_5coder7B`	`qwen2.5-coder:7b-instruct`	AliBaba's Qwen2.5 7b
`Qwen2_5oder7Bq8`	`qwen2.5-coder:7b-instruct-q8_0`	AliBaba's Qwen2.5 7b 8bit
`Qwen2_5coder7Bf16`	`qwen2.5-coder:7b-instruct-fp16`	AliBaba's Qwen2.5 7b 16bit
`QwenQwq`	`qwq`	AliBaba's QwenQwq
`DeepSeekCoder6_7B`	`deepseek-coder:6.7b`	DeepSeek Coding models
`Mixtral8_7b`	`mixtral:8x7b`	Mistral's MoE Models
`GPT4Turbo`	`gpt-4-turbo`	OpenAI's GPT-4 Turbo model
`GPT4o`	`gpt-4o`	OpenAI's GPT-4o model
`GPT4oMini`	`gpt-4o-mini`	OpenAI's GPT-4o mini model
`O1Mini`	`o1-mini`	OpenAI's o1 mini model
`O1Preview`	`o1-preview`	OpenAI's o1 preview model
`Gemini15ProExp0827`	`gemini-1.5-pro-exp-0827`	Gemini 1.5 Pro model
`Gemini15Pro`	`gemini-1.5-pro`	Gemini 1.5 Pro model
`Gemini15Flash`	`gemini-1.5-flash`	Gemini 1.5 Flash model
`Gemini10Pro`	`gemini-1.0-pro`	Gemini 1.0 Pro model
`Gemma2_2bIt`	`gemma-2-2b-it`	Gemma 2 2B IT model
`Gemma2_9bIt`	`gemma-2-9b-it`	Gemma 2 9B IT model
`Gemma2_27bIt`	`gemma-2-27b-it`	Gemma 2 27B IT model
`ORLlama3_1_8B`	`meta-llama/llama-3.1-8b-instruct`	OpenRouter Models
`ORLlama3_1_70B`	`meta-llama/llama-3.1-70b-instruct`	OpenRouter Models
`ORLlama3_1_405B`	`meta-llama/llama-3.1-405b-instruct`	OpenRouter Models
`ORLlama3_1_70BFree`	`meta-llama/llama-3.1-70b-instruct:free`	OpenRouter Models
`ORLlama3_3_70B`	`meta-llama/llama-3.3-70b-instruct`	OpenRouter Models
`OR3_5Sonnet`	`anthropic/claude-3.5-sonnet:beta`	OpenRouter Models
`OR3_5Haiku`	`anthropic/claude-3-5-haiku-20241022:beta`	OpenRouter Models
`ORQwen2_5_72B`	`qwen/qwen-2.5-72b-instruct`	OpenRouter Models
`ORQwen2_5_7B`	`qwen/qwen-2.5-7b-instruct`	OpenRouter Models
`ORQwen2_5Coder32B`	`qwen/qwen-2.5-coder-32b-instruct`	OpenRouter Models
`ORQwen2_5Eva32B`	`eva-unit-01/eva-qwen-2.5-32b`	OpenRouter Models
`ORQwenQwq`	`qwen/qwq-32b-preview`	OpenRouter Models
`ORDeepSeek2_5`	`deepseek/deepseek-chat`	OpenRouter Models
`ORNousHermes405B`	`nousresearch/hermes-3-llama-3.1-405b`	OpenRouter Models
`ORNemotron70B`	`nvidia/llama-3.1-nemotron-70b-instruct`	OpenRouter Models