Skip to content
Qwen

Qwen2.5 Coder 32B Instruct

Maker’s page
Check price at Amazon for Qwen (Alibaba Cloud) Qwen2.5-Coder-32B-Instruct (affiliate link, opens in new tab)
Weights at 16-bit
66 GB
Weights at 8-bit (Q8_0)
35 GB
Weights at 4-bit (Q4_K_M)
20 GB
Smallest card at 4-bit
GeForce RTX 3090 · 24 GB
Parameters
Layers
KV heads
Context
Licence

Specs

Attention heads
Context
Downloads (30 days)
GGUF downloads
repobytesfilesquant
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF16,635,834,7843 entriesQ2_K
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF23,875,161,8243 entriesQ3_K_M
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF29,349,797,1204 entriesQ4_0
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF31,712,551,4884 entriesQ4_K_M
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF37,358,996,2244 entriesQ5_0
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF38,610,783,5204 entriesQ5_K_M
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF45,784,950,0485 entriesQ6_K
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF61,772,055,3926 entriesQ8_0
Qwen/Qwen2.5-Coder-32B-Instruct-GGUF65,535,970,4649 entriesF16
Head size
Hidden size
KV heads
Layers
Licence
Parameters
Parameters by type
Publisher
Task

More from Qwen (Alibaba Cloud)