Skip to content
Qwen

Qwen2.5 0.5B Instruct

Maker’s page
Check price at Amazon for Qwen (Alibaba Cloud) Qwen2.5-0.5B-Instruct (affiliate link, opens in new tab)
Weights at 16-bit
1.0 GB
Weights at 8-bit (Q8_0)
0.5 GB
Weights at 4-bit (Q4_K_M)
0.3 GB
Smallest card at 4-bit
Intel Arc A380 · 6 GB
Parameters
Layers
KV heads
Context
Licence

Specs

Attention heads
Context
Downloads (30 days)
GGUF downloads
repobytesfilesquant
Qwen/Qwen2.5-0.5B-Instruct-GGUF415,182,6881 entriesQ2_K
Qwen/Qwen2.5-0.5B-Instruct-GGUF428,730,2081 entriesQ4_0
Qwen/Qwen2.5-0.5B-Instruct-GGUF432,041,8241 entriesQ3_K_M
Qwen/Qwen2.5-0.5B-Instruct-GGUF490,475,3601 entriesQ5_0
Qwen/Qwen2.5-0.5B-Instruct-GGUF491,400,0321 entriesQ4_K_M
Qwen/Qwen2.5-0.5B-Instruct-GGUF522,186,5921 entriesQ5_K_M
Qwen/Qwen2.5-0.5B-Instruct-GGUF650,379,1041 entriesQ6_K
Qwen/Qwen2.5-0.5B-Instruct-GGUF675,710,8161 entriesQ8_0
Qwen/Qwen2.5-0.5B-Instruct-GGUF1,266,425,6961 entriesF16
Head size
Hidden size
KV heads
Layers
Licence
Parameters
Parameters by type
Publisher
Task

More from Qwen (Alibaba Cloud)