Models · Catalogue

Every open-weight model worth hosting.

The LeemerLabs catalogue is a deliberately curated shortlist of open-weight models that justify their cost of inference. Hosted in Ireland on Nvidia H200s. OpenAI-compatible. Fine-tunable through Foundry.

Currently live

Our starting models.

Two founding models on our gateway: one for speed, one for depth. Both free on the public tier, both fine-tunable, both served on Nvidia H200s in Ireland.

Read the full brief

Coming up on the gateway

The full catalogue.

Models available for fine-tuning through Foundry today, with rolling availability on the public gateway. Request access if you need a specific model live sooner.

Request model

LeemerLabs

In-house

  • LeemerGLM-106B-A22BMoE · 22B active · Vision · 96K ctx
  • Liquid-LeemerLabs-350M350M · LoRA-ready · Insane speed

Gemma

Google DeepMind · Dense · MoE

  • Gemma 4 E2B2.3B eff · Text, Image, Audio · 128K
  • Gemma 4 E4B4.5B eff · Text, Image, Audio · 128K
  • Gemma 4 26B A4B25.2B · 3.8B active · MoE · 256K · live
  • Gemma 4 31B30.7B dense · Vision · 256K

Qwen

Dense · MoE · Vision

  • Qwen3-4B-Instruct-25074B · Instruct
  • Qwen3-8B-Base / Instruct8B
  • Qwen3-32B MoE32B · MoE
  • Qwen3-30B-A3B30B · 3B active · Base / Instruct
  • Qwen3-235B-A22B-Instruct-2507235B · 22B active · frontier
  • Qwen3-VL-30B-A3B-InstructVision · MoE
  • Qwen3-VL-235B-A22B-InstructVision · MoE · frontier

LLaMA

Meta · Dense

  • Llama-3.2-1B / 3BSmall dense
  • Llama-3.1-8B / Instruct8B
  • Llama-3.1-70B70B
  • Llama-3.3-70B-Instruct70B · latest

GPT-OSS

OpenAI open-weights

  • GPT-OSS-20B20B · MoE
  • GPT-OSS-120B120B · MoE

DeepSeek

MoE reasoning

  • DeepSeek V3.1 BaseMoE
  • DeepSeek V3.1 InstructMoE

Moonshot AI

Frontier reasoning

  • Kimi K2 ThinkingReasoning
  • Kimi K2.5 BaseFrontier · Multimodal

Gateway capabilities

What the API does.

supported

OpenAI-compatible

Drop-in at api.leemerlabs.ie/v1. Existing SDKs just work.

supported

Streaming + tools

SSE streaming, tool calling, JSON mode, structured output.

supported

Vision inputs

For VL models, image uploads follow the OpenAI vision schema.

supported

Fine-tuning

Every open-weight base on this page can be fine-tuned through Foundry.

Nvidia

Served on

Nvidia H200

141 GB HBM3e · Waterford & Dublin

Every request served on European metal. Zero trans-Atlantic hops.