Meta
Llama 3.3 70B Instruct
Check price at Amazon for Meta Llama 3.3 70B Instruct (affiliate link, opens in new tab)Affiliate link
- Weights at 16-bit
- 140 GB
- Weights at 8-bit (Q8_0)
- 74 GB
- Weights at 4-bit (Q4_K_M)
- 42 GB
- Smallest card at 4-bit
- RTX 6000 Ada Generation · 48 GB
- Parameters
- Layers
- KV heads
- Licence
Specs
- Attention heads
- Downloads (30 days)
- Family
- GGUF downloads
-
repo bytes files quant bartowski/Llama-3.3-70B-Instruct-GGUF 16,751,201,248 1 entries IQ1_M bartowski/Llama-3.3-70B-Instruct-GGUF 19,097,390,048 1 entries IQ2_XXS bartowski/Llama-3.3-70B-Instruct-GGUF 21,142,113,248 1 entries IQ2_XS bartowski/Llama-3.3-70B-Instruct-GGUF 22,242,348,000 1 entries IQ2_S bartowski/Llama-3.3-70B-Instruct-GGUF 24,119,299,040 1 entries IQ2_M bartowski/Llama-3.3-70B-Instruct-GGUF 26,375,113,696 1 entries Q2_K bartowski/Llama-3.3-70B-Instruct-GGUF 27,401,161,696 1 entries Q2_K_L bartowski/Llama-3.3-70B-Instruct-GGUF 27,469,499,360 1 entries IQ3_XXS bartowski/Llama-3.3-70B-Instruct-GGUF 29,307,735,008 1 entries IQ3_XS bartowski/Llama-3.3-70B-Instruct-GGUF 30,912,056,288 1 entries Q3_K_S bartowski/Llama-3.3-70B-Instruct-GGUF 31,937,039,328 1 entries IQ3_M bartowski/Llama-3.3-70B-Instruct-GGUF 34,267,499,488 1 entries Q3_K_M bartowski/Llama-3.3-70B-Instruct-GGUF 37,140,597,728 1 entries Q3_K_L bartowski/Llama-3.3-70B-Instruct-GGUF 37,902,666,720 1 entries IQ4_XS bartowski/Llama-3.3-70B-Instruct-GGUF 38,059,936,736 1 entries Q3_K_XL bartowski/Llama-3.3-70B-Instruct-GGUF 39,969,737,696 1 entries Q4_0_4_4 bartowski/Llama-3.3-70B-Instruct-GGUF 39,969,737,696 1 entries Q4_0_4_8 bartowski/Llama-3.3-70B-Instruct-GGUF 39,969,737,696 1 entries Q4_0_8_8 bartowski/Llama-3.3-70B-Instruct-GGUF 40,053,623,776 1 entries IQ4_NL bartowski/Llama-3.3-70B-Instruct-GGUF 40,116,538,336 1 entries Q4_0 bartowski/Llama-3.3-70B-Instruct-GGUF 40,347,225,056 1 entries Q4_K_S bartowski/Llama-3.3-70B-Instruct-GGUF 42,520,398,816 1 entries Q4_K_M bartowski/Llama-3.3-70B-Instruct-GGUF 43,300,195,296 1 entries Q4_K_L bartowski/Llama-3.3-70B-Instruct-GGUF 48,657,452,000 1 entries Q5_K_S bartowski/Llama-3.3-70B-Instruct-GGUF 49,949,822,112 2 entries Q5_K_M bartowski/Llama-3.3-70B-Instruct-GGUF 50,598,284,448 2 entries Q5_K_L bartowski/Llama-3.3-70B-Instruct-GGUF 57,888,148,672 2 entries Q6_K bartowski/Llama-3.3-70B-Instruct-GGUF 58,397,068,448 2 entries Q6_K_L bartowski/Llama-3.3-70B-Instruct-GGUF 74,975,055,008 2 entries Q8_0 bartowski/Llama-3.3-70B-Instruct-GGUF 141,117,918,624 4 entries F16 - Hidden size
- KV heads
- Layers
- Licence
- Parameters
- Parameters by type
- Publisher
- Released
- Task