qwen2
3B, 7B, 14B, 32B, coder-32B
How to use it
qwen2 is exposed by the Mercury MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the qwen2 tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Mercury MCP
pip install -e .Other tools in Mercury MCP (16)
22B (mistral coder variant)
35B (Cohere)
7B
9B
3.1-dense-8B (IBM)
7B
3.1-8B, 3.3-70B
Paper status, citations, contribution info
List all 23 observed models
7B-v0.3, small-3.2-24B
7B (AllenAI fully-open)
medium-14B
15B
hooked into llamacpp.Llama.logitsprocessor to capture output-layer hot dims per token
transformers.AutoModelForCausalLM.frompretrained with outputhiddenstates=True, per-layer residual stream activation magnitudes binned into 10 quantiles
1.5-9B