Codellama 70B Instruct Hf
Codellama 70B Instruct Hf is a 70 billion parameter language model part of Meta's open-weight Llama family. It is released under Meta's Llama Community License.
Input
Output
Context
16K
Max Output
16K
Parameters
70B
Technical Specifications
Model TypeChat
Context Window16K
Max Output Tokens16K
Parameters70B
Training Cutoff—
Licensellama2
Capabilities
Input Modalities
text
Output Modalities
text
Features
function_callingjson_modereasoningstreamingtext_generation
Benchmarks
#237
Rank (Text)
+17/-17
arena text ci 95
1065
Arena Score (Text)
1,192
Votes (Text)
Resources & Links
Estimated GPU Requirements for Codellama 70B Instruct Hf
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Apr 16, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.