278 Downloads Updated 1 year ago
New state-of-the-art model from Meta available in 8B, 70B and 405B sizes
Models
View all →Name
34 models
llama3.1-70b:latest
40GB · 128K context window · Text · 1 year ago
llama3.1-70b:q2_k
26GB · 128K context window · Text · 1 year ago
llama3.1-70b:q3_k_s
31GB · 128K context window · Text · 1 year ago
llama3.1-70b:q3_k_m
34GB · 128K context window · Text · 1 year ago
llama3.1-70b:q3_k_l
37GB · 128K context window · Text · 1 year ago
llama3.1-70b:q4_0
40GB · 128K context window · Text · 1 year ago
llama3.1-70b:q4_k_s
40GB · 128K context window · Text · 1 year ago
llama3.1-70b:q4_k_m
43GB · 128K context window · Text · 1 year ago
llama3.1-70b:q5_0
49GB · 128K context window · Text · 1 year ago
llama3.1-70b:q5_k_s
49GB · 128K context window · Text · 1 year ago
llama3.1-70b:q5_k_m
50GB · 128K context window · Text · 1 year ago
llama3.1-70b:q6_k
58GB · 128K context window · Text · 1 year ago
llama3.1-70b:q8_0
75GB · 128K context window · Text · 1 year ago
llama3.1-70b:iq2_xs
21GB · 128K context window · Text · 1 year ago
llama3.1-70b:iq2_s
22GB · 128K context window · Text · 1 year ago
llama3.1-70b:iq3_xxs
27GB · 128K context window · Text · 1 year ago
llama3.1-70b:iq3_xs
29GB · 128K context window · Text · 1 year ago
llama3.1-70b:iq3_s
31GB · 128K context window · Text · 1 year ago
llama3.1-70b:iq4_xs
38GB · 128K context window · Text · 1 year ago
llama3.1-70b:iq4_nl
40GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q2_k
26GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q3_k_s
31GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q3_k_m
34GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q4_0
40GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q4_k_m
43GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q5_0
49GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q5_k_s
49GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q5_k_m
50GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q6_k
58GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-q8_0
75GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-iq2_xs
21GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-iq3_s
31GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-iq4_xs
38GB · 128K context window · Text · 1 year ago
llama3.1-70b:tools-iq4_nl
40GB · 128K context window · Text · 1 year ago
Readme
Meta Llama 3.1
Llama 3.1 family of models available:
- 8B
- 70B
- 405B
Llama 3.1 405B is the first openly available model that rivals the top AI models when it comes to state-of-the-art capabilities in general knowledge, steerability, math, tool use, and multilingual translation.
The upgraded versions of the 8B and 70B models are multilingual and have a significantly longer context length of 128K, state-of-the-art tool use, and overall stronger reasoning capabilities. This enables Meta’s latest models to support advanced use cases, such as long-form text summarization, multilingual conversational agents, and coding assistants.
Meta also has made changes to their license, allowing developers to use the outputs from Llama models, including the 405B model, to improve other models.
Model evaluations
For this release, Meta has evaluation the performance on over 150 benchmark datasets that span a wide range of languages. In addition, Meta performed extensive human evaluations that compare Llama 3.1 with competing models in real-world scenarios. Meta’s experimental evaluation suggests that our flagship model is competitive with leading foundation models across a range of tasks, including GPT-4, GPT-4o, and Claude 3.5 Sonnet. Additionally, Meta’s smaller models are competitive with closed and open models that have a similar number of parameters.