Qwen
Qwen2.5 7B Instruct
Check price at Amazon for Qwen (Alibaba Cloud) Qwen2.5 7B Instruct (affiliate link, opens in new tab)Affiliate link
- 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
-
repo bytes files quant Qwen/Qwen2.5-7B-Instruct-GGUF 3,015,940,000 1 entries Q2_K Qwen/Qwen2.5-7B-Instruct-GGUF 3,808,391,072 1 entries Q3_K_M Qwen/Qwen2.5-7B-Instruct-GGUF 4,431,390,848 2 entries Q4_0 Qwen/Qwen2.5-7B-Instruct-GGUF 4,683,073,632 2 entries Q4_K_M Qwen/Qwen2.5-7B-Instruct-GGUF 5,315,176,576 2 entries Q5_0 Qwen/Qwen2.5-7B-Instruct-GGUF 5,444,831,360 2 entries Q5_K_M Qwen/Qwen2.5-7B-Instruct-GGUF 6,254,198,880 2 entries Q6_K Qwen/Qwen2.5-7B-Instruct-GGUF 8,098,525,408 3 entries Q8_0 Qwen/Qwen2.5-7B-Instruct-GGUF 15,237,853,536 4 entries F16 - Head size
- Hidden size
- KV heads
- Layers
- Licence
- Parameters
- Parameters by type
- Publisher
- Released
- Task