Open model lab
Big models, small machines
Sapid Labs quantizes and prunes open LLMs so they run on the hardware in front of you. Laptops, single GPUs, home rigs. We ship the weights on Hugging Face, free to use.
Quantize
4-bit, 8-bit, GGUF, AWQ. We squeeze weights down so big models fit in the memory you actually have.
Prune
Expert pruning and REAP on MoE models. Fewer experts, same feel, a fraction of the footprint.
Benchmark
Every release ships with real tok/s and quality numbers on real local hardware. No hand waving.
Latest models
All on Hugging FaceMistral-Large-4-667B-A52B-REAP-NVFP4
From mistralai/Mistral-Large-4-1T-A52B-NVFP4
Raon-1-mini-preview-NVFP4-GPTQ
From KRAFTON/Raon-1-mini-preview
LFM2.5-24B-A2B-NVFP4-W4A16
From LiquidAI/LFM2.5-24B-A2B
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-NVFP4-W4A16
From nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
Sparkulator-Qwen3.6-27B
From nvidia/Qwen3.6-27B-NVFP4
Sparkulator-Gemma-4-26B-A4B
From google/gemma-4-26B-A4B-it-assistant
Sparkulator-Laguna-S-2.1
From poolside/Laguna-S-2.1-DFlash-FP8
Sparkulator-Laguna-S-2.1-NVFP4
From poolside/Laguna-S-2.1-DFlash-NVFP4
Sparkulator-Laguna-XS-2.1
From poolside/Laguna-XS-2.1-DFlash
Sparkulator-GLM-5.2
From RedHatAI/GLM-5.2-speculator.dspark
GLM-5.2-NVFP4-attn-experimental
From zai-org/GLM-5.2-FP8
GLM-5.2-2bit-MoE-planes-pruned208-tp2
From zai-org/GLM-5.2-FP8
