models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Simia-AgentBench-SFT-Qwen2.5-7B-i1-GGUFSimia-AgentBench-SFT-Qwen2.5-7B-GGUFqwen2.5-1.5b-reasoning-GGUFqwen25_7b_agentbench_lora-16bitagent-bench-alfworld-merged3TinyTale-15Magentbench-qwen3-4b-lr5e6-20260224v2agentbench-qwen3-4b-2stage-reasoning-20260228agentbench-qwen3-4b-alf-20260301-lr1e6-v6qwen3-4b-agentbench-opd-mergedqwen3-4b-agentbench-opd-adapter-v2qwen25_7b_lora_agentbench_v11qwen3-4b-agentbench-opdagentbench-qwen3-4b-lr5e6-20260225qwen3-4b-agentbench-opd-merged-v2-sampleagentbench-qwen3-4b-2stage-db-20260302-lr1e6qwen2.5-7b-agentbench-v8Qwen3-4B-AgentBench-Merged-v2-11agentbench-qwen3-4b-2stage-reasoning-20260228-lr2e6qwen25_7b_lora_agentbench_v13agentbench-qwen3-4b-alf-20260301-lr1e6-v4Qwen3-4B-AgentBench-Merged-v2-16Qwen3-4B-AgentBench-Merged-v2-5Qwen3-4B-AgentBench-Merged-v2-6Qwen3-4B-AgentBench-Merged-v2-9Qwen3-4B-AgentBench-Merged-v2-10qwen25_7b_lora_agentbench_v23_e1agentbench-qwen3-4b-2stage-db-20260302-lr1e6-v3qwen3-4b-agentbench-opd-merged-v2qwen25_7b_lora_agentbench_v6