Open-Weight LLM Models — Live Ranking, Benchmarks & Specs
Explore, filter and compare open-weight language models with live specs, benchmarks and license data
Qwen3.8-Flash-Next
Qwen Team (Alibaba)
Hybrid Attention (Gated DeltaNet + Qwen Sparse Attention) with MoE, N-gram Embedding, and Gated Residual
Qwen
Qwen Community License 1.0
Openness Score
0.7
Qwen3.8-2.4T-A95B
Qwen
92-layer hybrid MoE: 23 x (3 x (Gated DeltaNet -> MoE) + 1 x (Gated Attention -> MoE)); 512 experts (10 routed + 1 shared, dim 2048); hidden 8192; GDN 128V/16QK dim 128; GA 64Q/4KV dim 256; MTP multi-steps; ctx 262144 -> 1010000.
Qwen3.8
Qwen3.8-Max License
Openness Score
0.7
Qwen3.8-27B
Qwen Team (Alibaba Cloud)
Hybrid Gated DeltaNet + Gated Attention (dense, vision-language)
Qwen3.8
Apache License 2.0
Openness Score
1.0
Qwen-AgentWorld-35B-A3B
Qwen Team (Alibaba Cloud)
Hybrid Gated DeltaNet + Gated Attention MoE - Language World Model (qwen3_5_moe)
Qwen-AgentWorld
Apache License 2.0
Openness Score
1.0
Qwen3.6-27B
Qwen Team (Alibaba Cloud)
Hybrid Gated DeltaNet + Gated Attention (dense)
Qwen3.6
Apache License 2.0
Openness Score
1.0
Qwen3.6-35B-A3B
Qwen Team (Alibaba Cloud)
Hybrid Gated DeltaNet + Gated Attention MoE
Qwen3.6
Apache License 2.0
Openness Score
1.0
Qwen3.5-4B
Qwen
Causal Language Model with Vision Encoder - Hybrid Gated Delta Networks + Gated Attention (dense FFN)
Qwen3.5
Apache License 2.0
Openness Score
1.0
Qwen3.5-27B
Qwen Team (Alibaba Cloud)
Hybrid Gated DeltaNet + Gated Attention
Qwen3.5
Apache License 2.0
Openness Score
1.0
Qwen3.5-122B-A10B
Qwen Team (Alibaba Cloud)
Hybrid Gated DeltaNet + Gated Attention MoE
Qwen3.5
Apache License 2.0
Openness Score
1.0
Qwen3.5-35B-A3B
Qwen Team (Alibaba Cloud)
Hybrid Gated DeltaNet + Gated Attention MoE
Qwen3.5
Apache License 2.0
Openness Score
1.0
Qwen3.5-2B
Qwen Team (Alibaba Cloud)
Causal Language Model with Vision Encoder - Hybrid Gated Delta Networks + Gated Attention (dense FFN)
Qwen3.5
Apache License 2.0
Openness Score
1.0
Qwen3-Coder-Next
Qwen
Causal Language Model
Qwen3
Apache License 2.0
Openness Score
1.0
Qwen3-VL-30B-A3B
Qwen
Mixture-of-Experts Vision-Language Transformer
Qwen3-VL
Apache License 2.0
Openness Score
1.0
Open Weights
Mixture-of-Experts Transformer with Thinking mode
Qwen3-Next
Apache License 2.0
Openness Score
1.0
Open Weights
Mixture-of-Experts Transformer with Thinking mode
Qwen3
Apache License 2.0
Openness Score
1.0
Qwen3-235B-A22B
Qwen Team (Alibaba Cloud)
Mixture-of-Experts Transformer with Thinking mode
Qwen3
Apache License 2.0
Openness Score
1.0
Qwen3-30B-A3B
Qwen
Mixture-of-Experts Transformer with Hybrid Thinking Mode
Qwen3
Apache License 2.0
Openness Score
1.0