darkmaniac7/Qwen3-0.6B-kl-baseline-20k-MNN
Text Generation • Updated • 145
TokForge Mobile Draft Models
Small MNN draft models and speculative-decoding bundles for TokForge on Android. Includes practical Qwen3 0.6B drafts plus experimental variants.
Note Practical baseline 20K Qwen3 0.6B draft for TokForge + MNN. About +30% on RedMagic 8B in our preserved short-run packet.
darkmaniac7/Qwen3-0.6B-lk-alpha-20k-MNN
Text Generation • Updated • 150Note Acceptance-oriented 20K LK Alpha variant. Similar device uplift band to the KL baseline, useful comparison artifact.
darkmaniac7/Qwen3-0.6B-lk-alpha-40k-MNN
Text Generation • Updated • 140Note Experimental 40K LK Alpha draft. Research comparison artifact rather than the default recommendation.
darkmaniac7/Qwen3-0.6B-lk-alpha-14b-paired-MNN
Text Generation • Updated • 145Note Experimental 14B-paired Qwen3 draft for more target-specific speculative decoding experiments.
darkmaniac7/Qwen3.5-0.8B-lk-alpha-ep4-MNN
Text Generation • UpdatedNote Experimental Qwen3.5 0.8B draft bundle. Uploaded for reproducibility and research, not the main practical recommendation.