HuggingFaceBio/Carbon-8B-GGUF

Cleanup: drop SHA256 column + remove stale Files section

Expand quant table with K-quants

Add Q4_K_M quantization

Add Q5_K_M quantization

Add Q6_K quantization

Add Q8_0 quant info + Mac/llama-completion note

Add Q8_0 quantization

Re-convert without chat template

Re-convert with k-mer collision fix (marker)

card: add llama-server speculative decoding example

card: HybridDNATokenizer merged upstream (#23410)

card: add download step

Add bf16 GGUF

card: add metadata conditioning, YaRN, likelihood, FNS note

card: add draft-model download instructions

Add model card

initial commit