Skip to content
Qwen

Qwen2.5 Coder 3B Instruct

Maker’s page
Check price at Amazon for Qwen (Alibaba Cloud) Qwen2.5-Coder-3B-Instruct (affiliate link, opens in new tab)
Weights at 16-bit
6.2 GB
Weights at 8-bit (Q8_0)
3.3 GB
Weights at 4-bit (Q4_K_M)
1.9 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-Coder-3B-Instruct-GGUF1,376,856,5121 entriesQ2_K
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF1,724,178,8801 entriesQ3_K_M
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF1,997,879,7441 entriesQ4_0
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF2,104,932,8001 entriesQ4_K_M
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF2,383,591,8721 entriesQ5_0
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF2,438,740,4161 entriesQ5_K_M
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF2,793,411,0081 entriesQ6_K
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF3,616,088,5121 entriesQ8_0
Qwen/Qwen2.5-Coder-3B-Instruct-GGUF6,800,646,5921 entriesF16
Head size
Hidden size
KV heads
Layers
Licence
Parameters
Parameters by type
Publisher
Task

More from Qwen (Alibaba Cloud)