Skip to content
Qwen

Qwen2.5 7B Instruct

Maker’s page
Check price at Amazon for Qwen (Alibaba Cloud) Qwen2.5 7B Instruct (affiliate link, opens in new tab)
Weights at 16-bit
15 GB
Weights at 8-bit (Q8_0)
8.1 GB
Weights at 4-bit (Q4_K_M)
4.6 GB
Smallest card at 4-bit
Intel Arc A380 · 6 GB
Parameters
Layers
KV heads
Context
Licence

Specs

Attention heads
Context
Downloads (30 days)
Family
GGUF downloads
repobytesfilesquant
Qwen/Qwen2.5-7B-Instruct-GGUF3,015,940,0001 entriesQ2_K
Qwen/Qwen2.5-7B-Instruct-GGUF3,808,391,0721 entriesQ3_K_M
Qwen/Qwen2.5-7B-Instruct-GGUF4,431,390,8482 entriesQ4_0
Qwen/Qwen2.5-7B-Instruct-GGUF4,683,073,6322 entriesQ4_K_M
Qwen/Qwen2.5-7B-Instruct-GGUF5,315,176,5762 entriesQ5_0
Qwen/Qwen2.5-7B-Instruct-GGUF5,444,831,3602 entriesQ5_K_M
Qwen/Qwen2.5-7B-Instruct-GGUF6,254,198,8802 entriesQ6_K
Qwen/Qwen2.5-7B-Instruct-GGUF8,098,525,4083 entriesQ8_0
Qwen/Qwen2.5-7B-Instruct-GGUF15,237,853,5364 entriesF16
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