Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 F32 1752a47 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 F16 310bf7f verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 BF16 0f0a538 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q8_0 dec7afe verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q6_K 8b548c5 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q5_K_M ec5c215 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q5_K_S 3451d03 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q4_K_M 9e580b7 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q4_K_S 14da8e5 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q3_K_L ada5ba6 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q3_K_M 053bded verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q3_K_S e9ed5ff verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q2_K 889f2a2 verified jartine commited on May 10
Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.8.4 Q5_1 452f0d0 verified jartine commited on May 10