thinkingmachines/Inkling
21 derivatives checked
- unsloth/inkling-GGUF: Not comparable yet
- thinkingmachines/Inkling-NVFP4: Partial fine-tune (fewer layers)
- RedHatAI/Inkling-FP8-dynamic: Quantization
- inference-optimization/Inkling-0.6B-A0.6B: Different architecture
- lightseekorg/Inkling-MXFP4: Adapter
- AtomicChat/Inkling-GGUF: Not comparable yet
- mlx-community/Inkling-mlx-4bit: Quantization
- DragonBophades/Inkling-Gutenberg-DPO: Full fine-tune
- thunquant/Inkling-NVFP4: Partial fine-tune (fewer layers)
- trinityomni/Inkling-NVFP4: Partial fine-tune (fewer layers)
- biennequants/Inkling-NVFP4: Partial fine-tune (fewer layers)
- schwyzquants/Inkling-NVFP4: Partial fine-tune (fewer layers)
- RedHatAI/Inkling-NVFP4-FP8-BLOCK: Quantization
- mlx-community/Inkling-mlx-2bit: Quantization
- DevQuasar/thinkingmachines.Inkling-GGUF: Not comparable yet
- sabrewing-engine/Inkling-colibri-int4: Different architecture
- bielquants/Inkling-NVFP4: Partial fine-tune (fewer layers)
- unsloth/inkling-NVFP4: Partial fine-tune (fewer layers)
- baerquants/Inkling-NVFP4: Partial fine-tune (fewer layers)
- konizquants/Inkling-NVFP4: Partial fine-tune (fewer layers)
- yujiepan/inkling-tiny-random: Different architecture