meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 6.72M • • 6.65k
🧩 Long-Context Models (≥128k) CODING
10 CODING models that support ≥128k context (native or via officially documented scaling)
-
-
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.26M • • 1.46k -
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 958k • • 1.21k -
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Text Generation • 16B • Updated • 614k • 639 -
Qwen/Qwen2.5-Coder-32B-Instruct
Text Generation • 33B • Updated • 1.39M • • 2.11k -
agentica-org/DeepCoder-14B-Preview
Text Generation • 15B • Updated • 788 • • 680 -
unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF
Text Generation • 31B • Updated • 14k • 162 -
ibm-granite/granite-8b-code-base-128k
Text Generation • 8B • Updated • 164 • 7 -
mistralai/Codestral-22B-v0.1
22B • Updated • 40.5k • 1.35k -
microsoft/Phi-3-medium-128k-instruct
Text Generation • 14B • Updated • 21.7k • 389