Skip to main content
NeuroBrixNeuroBrix

Model Hub

Browse, search, and download AI models.

Compare models

deepseek-ai

DeepSeek-Coder-V2-Lite-Instruct

CODE

DeepSeek-Coder-V2-Lite-Instruct — 15.7B-A2.4B code specialist; MLA attention (kv_lora 512, qk 128+64, v 128) + YaRN-mscale, MoE 64+2 experts top-6

codemoemlayarn+1
3829.9 GiB
DeepSeek

Qwen

Qwen3-Coder-30B-A3B-Instruct

CODE

Qwen3-Coder 30B-A3B Instruct — Qwen's MoE coding model (48 layers, 128 experts top-8, 3B active) tuned for agentic coding, with native 262k-token context. Apache 2.0.

CodeCodingMixture-of-ExpertsAgentic Coding+3
2856.9 GiB
Apache 2.0