Skip to content
$ Language Pipes

Supported Models

Supported model families

  • Qwen3 (dense)
  • Qwen3-MoE (mixture-of-experts)
  • Phi (Phi-3 / Phi-4 architecture)
  • Meta Llama (Llama 2 and Llama 3.x)
  • Gemma 3
  • Gemma 4
  • Ministral 3

Note: Any fine-tuned model based on a supported base architecture should also work.

Tested checkpoints

Below are the specific checkpoints that have been tested and are known to work.

Qwen3:

  • Qwen/Qwen3-0.6B
  • Qwen/Qwen3-1.7B
  • Qwen/Qwen3-14B

Qwen/3.5:

  • Qwen/Qwen3.5-0.8B
  • Qwen/Qwen3.5-2B
  • Qwen/Qwen3.5-4B
  • Qwen/Qwen3.5-9B
  • Qwen/Qwen3.5-27B

Qwen3-MoE:

  • Qwen/Qwen3-30B-A3B-Thinking-2507

Phi:

  • microsoft/phi-4
  • microsoft/Phi-4-reasoning
  • microsoft/Phi-4-mini-instruct
  • microsoft/Phi-4-mini-reasoning
  • microsoft/Phi-4-reasoning-plus

Meta Llama:

  • meta-llama/Llama-2-7b
  • meta-llama/Llama-3.1-8B-Instruct
  • meta-llama/Llama-3.2-1B-Instruct
  • meta-llama/Llama-3.2-3B-Instruct
  • meta-llama/Llama-3.3-70B-Instruct

Gemma 3:

  • google/gemma-3-1b-it

Gemma 4:

  • google/gemma-4-E2B-it
  • google/gemma-4-E4B-it
  • google/gemma-4-12B-it
  • google/gemma-4-31B-it
  • google/gemma-4-26B-A4B-it

Ministral 3:

  • mistralai/Ministral-3-3B-Reasoning-2512
  • mistralai/Ministral-3-3B-Instruct-2512
  • mistralai/Ministral-3-8B-Instruct-2512
  • mistralai/Ministral-3-14B-Instruct-2512

Open AI:

  • openai/gpt-oss-20b