Qwen
Qwen2.5 32B Instruct
Check price at Amazon for Qwen (Alibaba Cloud) Qwen2.5 32B Instruct (affiliate link, opens in new tab)Affiliate link
- Weights at 16-bit
- 65 GB
- Weights at 8-bit (Q8_0)
- 35 GB
- Weights at 4-bit (Q4_K_M)
- 20 GB
- Smallest card at 4-bit
- GeForce RTX 3090 · 24 GB
- Parameters
- Layers
- KV heads
- Context
- Licence
Specs
- Attention heads
- Context
- Downloads (30 days)
- Family
- GGUF downloads
-
repo bytes files quant bartowski/Qwen2.5-32B-Instruct-GGUF 9,028,250,496 1 entries IQ2_XXS bartowski/Qwen2.5-32B-Instruct-GGUF 9,957,550,976 1 entries IQ2_XS bartowski/Qwen2.5-32B-Instruct-GGUF 10,387,569,536 1 entries IQ2_S bartowski/Qwen2.5-32B-Instruct-GGUF 11,264,441,216 1 entries IQ2_M bartowski/Qwen2.5-32B-Instruct-GGUF 12,313,099,136 1 entries Q2_K bartowski/Qwen2.5-32B-Instruct-GGUF 13,073,419,136 1 entries Q2_K_L bartowski/Qwen2.5-32B-Instruct-GGUF 13,705,513,856 1 entries IQ3_XS bartowski/Qwen2.5-32B-Instruct-GGUF 14,392,331,136 1 entries Q3_K_S bartowski/Qwen2.5-32B-Instruct-GGUF 14,810,123,136 1 entries IQ3_M bartowski/Qwen2.5-32B-Instruct-GGUF 15,935,048,576 1 entries Q3_K_M bartowski/Qwen2.5-32B-Instruct-GGUF 17,247,079,296 1 entries Q3_K_L bartowski/Qwen2.5-32B-Instruct-GGUF 17,693,154,176 1 entries IQ4_XS bartowski/Qwen2.5-32B-Instruct-GGUF 17,928,326,016 1 entries Q3_K_XL bartowski/Qwen2.5-32B-Instruct-GGUF 18,640,231,296 1 entries Q4_0_4_4 bartowski/Qwen2.5-32B-Instruct-GGUF 18,640,231,296 1 entries Q4_0_4_8 bartowski/Qwen2.5-32B-Instruct-GGUF 18,640,231,296 1 entries Q4_0_8_8 bartowski/Qwen2.5-32B-Instruct-GGUF 18,711,010,176 1 entries Q4_0 bartowski/Qwen2.5-32B-Instruct-GGUF 18,784,410,496 1 entries Q4_K_S bartowski/Qwen2.5-32B-Instruct-GGUF 19,851,336,576 1 entries Q4_K_M bartowski/Qwen2.5-32B-Instruct-GGUF 20,429,179,776 1 entries Q4_K_L bartowski/Qwen2.5-32B-Instruct-GGUF 22,638,254,976 1 entries Q5_K_S bartowski/Qwen2.5-32B-Instruct-GGUF 23,262,157,696 1 entries Q5_K_M bartowski/Qwen2.5-32B-Instruct-GGUF 23,742,679,936 1 entries Q5_K_L bartowski/Qwen2.5-32B-Instruct-GGUF 26,886,155,136 1 entries Q6_K bartowski/Qwen2.5-32B-Instruct-GGUF 27,263,273,856 1 entries Q6_K_L bartowski/Qwen2.5-32B-Instruct-GGUF 34,820,885,376 1 entries Q8_0 bartowski/Qwen2.5-32B-Instruct-GGUF 65,535,970,112 2 entries F16 - Head size
- Hidden size
- KV heads
- Layers
- Licence
- Parameters
- Parameters by type
- Publisher
- Released
- Task