Skip to content
Qwen

Qwen2.5 1.5B Instruct

Maker’s page
Check price at Amazon for Qwen (Alibaba Cloud) Qwen2.5-1.5B-Instruct (affiliate link, opens in new tab)
Weights at 16-bit
3.1 GB
Weights at 8-bit (Q8_0)
1.6 GB
Weights at 4-bit (Q4_K_M)
0.9 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/Qwen2.5-1.5B-Instruct-GGUF752,880,1601 entriesQ2_K
Qwen/Qwen2.5-1.5B-Instruct-GGUF924,455,9681 entriesQ3_K_M
Qwen/Qwen2.5-1.5B-Instruct-GGUF1,066,227,2321 entriesQ4_0
Qwen/Qwen2.5-1.5B-Instruct-GGUF1,117,320,7361 entriesQ4_K_M
Qwen/Qwen2.5-1.5B-Instruct-GGUF1,259,173,4081 entriesQ5_0
Qwen/Qwen2.5-1.5B-Instruct-GGUF1,285,494,3041 entriesQ5_K_M
Qwen/Qwen2.5-1.5B-Instruct-GGUF1,464,178,7201 entriesQ6_K
Qwen/Qwen2.5-1.5B-Instruct-GGUF1,894,532,1281 entriesQ8_0
Qwen/Qwen2.5-1.5B-Instruct-GGUF3,560,416,2881 entriesF16
Head size
Hidden size
KV heads
Layers
Licence
Parameters
Parameters by type
Publisher
Task

More from Qwen (Alibaba Cloud)