Tencent
Hy3
- Weights at 16-bit
- 598 GB
- Weights at 8-bit (Q8_0)
- 317 GB
- Weights at 4-bit (Q4_K_M)
- 181 GB
- Smallest card at 4-bit
- More than one card
- Parameters
- Layers
- KV heads
- Context
- Licence
Specs
- Attention heads
- Context
- Downloads (30 days)
- Experts
- Experts per token
- GGUF downloads
-
repo bytes files quant bartowski/Hy3-GGUF 64,051,148,352 2 entries IQ1_S bartowski/Hy3-GGUF 71,100,724,800 2 entries IQ1_M bartowski/Hy3-GGUF 82,113,918,656 3 entries IQ2_XXS bartowski/Hy3-GGUF 91,060,369,120 3 entries IQ2_XS bartowski/Hy3-GGUF 92,805,134,016 3 entries IQ2_S bartowski/Hy3-GGUF 102,091,323,104 3 entries IQ2_M bartowski/Hy3-GGUF 106,691,229,376 3 entries Q2_K bartowski/Hy3-GGUF 107,174,557,408 3 entries Q2_K_L bartowski/Hy3-GGUF 126,089,361,248 4 entries IQ3_XXS bartowski/Hy3-GGUF 131,274,569,536 4 entries Q3_K_S bartowski/Hy3-GGUF 137,437,050,656 4 entries IQ3_XS bartowski/Hy3-GGUF 137,545,479,968 4 entries Q3_K_M bartowski/Hy3-GGUF 143,077,766,976 4 entries Q3_K_L bartowski/Hy3-GGUF 143,510,828,864 4 entries Q3_K_XL bartowski/Hy3-GGUF 143,668,639,584 4 entries IQ3_M bartowski/Hy3-GGUF 160,771,307,456 5 entries IQ4_XS bartowski/Hy3-GGUF 169,803,872,192 5 entries IQ4_NL bartowski/Hy3-GGUF 170,321,082,336 5 entries Q4_0 bartowski/Hy3-GGUF 175,458,318,304 5 entries Q4_K_S bartowski/Hy3-GGUF 182,158,227,360 5 entries Q4_K_M bartowski/Hy3-GGUF 182,525,556,640 5 entries Q4_K_L bartowski/Hy3-GGUF 187,795,601,344 5 entries Q4_1 bartowski/Hy3-GGUF 206,034,401,344 6 entries Q5_K_S bartowski/Hy3-GGUF 212,837,857,344 6 entries Q5_K_M bartowski/Hy3-GGUF 257,246,623,936 7 entries Q6_K bartowski/Hy3-GGUF 317,652,367,776 9 entries Q8_0 - Head size
- Hidden size
- KV heads
- Layers
- Licence
- Parameters
- Parameters by type
- Publisher
- Shared experts
- Task