manjunathshiva/gpt-oss-20b-tq3

docs: add turboquant-plan — check the fit before downloading

docs: add turboquant-plan — check the fit before downloading

Upload README.md with huggingface_hub

docs: drop broken mlx_lm.load snippet (turboquant-generate is the entry point)

Add sampler recommendations + 6-test stress verdicts (16 GB target verified)

v0.2: rewrite model card with turboquant-generate CLI + KV cache flags

Update README.md

Upload README.md with huggingface_hub

Upload model_card.md with huggingface_hub

Upload folder using huggingface_hub

initial commit