Skip to content
Qwen

Qwen2.5 72B Instruct

Maker’s page
Check price at Amazon for Qwen (Alibaba Cloud) Qwen2.5 72B Instruct (affiliate link, opens in new tab)
Weights at 16-bit
145 GB
Weights at 8-bit (Q8_0)
77 GB
Weights at 4-bit (Q4_K_M)
44 GB
Smallest card at 4-bit
RTX 6000 Ada Generation · 48 GB
Parameters
Layers
KV heads
Context
Licence

Specs

Attention heads
Context
Downloads (30 days)
Family
GGUF downloads
repobytesfilesquant
bartowski/Qwen2.5-72B-Instruct-GGUF23,740,212,8961 entriesIQ1_M
bartowski/Qwen2.5-72B-Instruct-GGUF25,490,024,0961 entriesIQ2_XXS
bartowski/Qwen2.5-72B-Instruct-GGUF27,057,645,2161 entriesIQ2_XS
bartowski/Qwen2.5-72B-Instruct-GGUF29,338,986,1441 entriesIQ2_M
bartowski/Qwen2.5-72B-Instruct-GGUF29,811,762,8481 entriesQ2_K
bartowski/Qwen2.5-72B-Instruct-GGUF31,028,274,8481 entriesQ2_K_L
bartowski/Qwen2.5-72B-Instruct-GGUF31,845,082,7841 entriesIQ3_XXS
bartowski/Qwen2.5-72B-Instruct-GGUF34,487,789,2161 entriesQ3_K_S
bartowski/Qwen2.5-72B-Instruct-GGUF35,503,597,2161 entriesIQ3_M
bartowski/Qwen2.5-72B-Instruct-GGUF37,698,725,5361 entriesQ3_K_M
bartowski/Qwen2.5-72B-Instruct-GGUF39,505,225,3761 entriesQ3_K_L
bartowski/Qwen2.5-72B-Instruct-GGUF39,709,075,1041 entriesIQ4_XS
bartowski/Qwen2.5-72B-Instruct-GGUF40,595,220,1281 entriesQ3_K_XL
bartowski/Qwen2.5-72B-Instruct-GGUF41,383,126,6881 entriesQ4_0
bartowski/Qwen2.5-72B-Instruct-GGUF47,415,715,4881 entriesQ4_K_M
bartowski/Qwen2.5-72B-Instruct-GGUF54,447,466,3362 entriesQ5_K_M
bartowski/Qwen2.5-72B-Instruct-GGUF64,347,629,4082 entriesQ6_K
bartowski/Qwen2.5-72B-Instruct-GGUF77,262,612,3202 entriesQ8_0
Head size
Hidden size
KV heads
Layers
Licence
Parameters
Parameters by type
Publisher
Released
Task

More Qwen2.5

Across the range 9 models by family