QUASAR-QAT/gemma-4-12B-it-QUASAR-Q4_0-GGUF

Add standard Q4_0 (llama-quantize, no imatrix) baseline row

Add standard Q4_0 (llama-quantize, no imatrix) baseline row

Chart: shorten the Unsloth repack label

Model card: reviewer pass (opener w/ Unsloth 2.2x, accurate Unsloth Q4_0 repack label, compact native-QAT, defensive CTA removed); metadata: +gemma-4-12b(+-it)/quantized/4-bit precision/weight-only/multimodal/capability tags, license_link; model-index keeps only the GGUF's own KL row

Add citation block

Link remaining checkpoint mentions: BF16 base, W4A16 twin, E4B repos, Google/Unsloth Q4_0 in speed line

Link every compared checkpoint to its exact HF file (README, EVAL)

QUASAR native Q4_0 GGUF + BF16 mmproj (private draft)

QUASAR native Q4_0 GGUF + BF16 mmproj (private draft)

QUASAR native Q4_0 GGUF + BF16 mmproj (private draft)

12B GGUF card v1: no chart

QUASAR native Q4_0 GGUF + BF16 mmproj (private draft)

QUASAR native Q4_0 GGUF + BF16 mmproj (private draft)

QUASAR native Q4_0 GGUF + BF16 mmproj (private draft)

initial commit