moravian.ai

moravian.ai · info@moravian.ai

CzechSpeech

CzechSpeech is a speech-to-text model (Whisper large-v3-turbo) fine-tuned on Czech speech by Moravian AI. It transcribes parliamentary speech, read speech and speech in noise more accurately than available open models of comparable size. Quantised to 4 bits it fits in 452 MiB and runs offline on a laptop or on an ordinary phone.

• CzechSpeech: transformers and whisper.cpp (q5_0, q4_0) · results: moravian.ai/czechspeech
• Dual licence: free for non-commercial use (CC BY-NC 4.0); commercial licence: info@moravian.ai

ThinCtx

ThinCtx-small: the quality of Qwen3.5 in a small GPU memory. Qwen3.5 converted so that the GPU memory for the context stays small and grows about 15 to 20 times more slowly than the original's cache, with the weights stored at 5.4 to 6.4 bits per weight and the context kept compressed in system memory. At 128k tokens the 4B-small needs 4.0 GB of GPU memory instead of 12.0 GB for the original, and at 540k tokens 4.7 GB instead of 24.5 GB.

• ThinCtx-Qwen3.5-4B-small · full precision: ThinCtx-Qwen3.5-4B
• ThinCtx-Qwen3.5-2B-small · full precision: ThinCtx-Qwen3.5-2B
• ThinCtx-Qwen3.5-0.8B-small · full precision: ThinCtx-Qwen3.5-0.8B (not recommended for tool calling)
• Runtime: pip install thinctx · results: moravian.ai/thinctx

ThinEmbed

The query side of an embedding model, compressed into a small file that runs in the browser on WebGPU, against your unchanged document index. Open source, Apache-2.0.

• harrier-0.6b (English): WebGPU clients · GGUF clients
• Qwen3-Embedding-0.6B (Czech): WebGPU client · GGUF client
• bge-m3 (Czech, multilingual): GGUF clients
• Packages: npm install @moravianai/thinembed-vq · pip install thinembed
• Demo · code · results: moravian.ai/query-encoders