Qwen3-Next-80B
An MoE-architecture large language model in Alibaba's Tongyi Qianwen series, with 80B parameters and a file size of approximately 48.4 GB. It contains multiple expert feed-forward networks, of which only a small number are activated per token.
Core Facts
Timeline (last 90 days)
Qwen3-Next-80B has a MoE architecture with about 80B total parameters, but each forward inference only activates about 3B parameters.
Janas runs the 48.4GB Qwen3-Next-80B on a 32GB-memory laptop at 37 tok/s; on the same machine and same model llama.cpp reaches only 2.8 tok/s.
Janas supports speculative decoding: a small draft model guesses the next few tokens and the large model verifies them in one pass. On Qwen3-Next-80B this raises write speed from 24 to 37 tok/s, with the text content completely identical.
On the test machine, Qwen3-Next-80B reads a 1024-token prompt at 62 tok/s and writes at 24 tok/s without the draft enabled; Qwen3-Coder-Next, also 48.4GB, reads at 66 and writes at 22.
All Facts (5)
The Qwen2.5:7B model is approximately 4 GB in size after Q4 quantization.
80%UnverifiedQwen3-Next-80B has a MoE architecture with about 80B total parameters, but each forward inference only activates about 3B parameters.
50%UnverifiedJanas runs the 48.4GB Qwen3-Next-80B on a 32GB-memory laptop at 37 tok/s; on the same machine and same model llama.cpp reaches only 2.8 tok/s.
50%UnverifiedJanas supports speculative decoding: a small draft model guesses the next few tokens and the large model verifies them in one pass. On Qwen3-Next-80B this raises write speed from 24 to 37 tok/s, with the text content completely identical.
50%UnverifiedOn the test machine, Qwen3-Next-80B reads a 1024-token prompt at 62 tok/s and writes at 24 tok/s without the draft enabled; Qwen3-Coder-Next, also 48.4GB, reads at 66 and writes at 22.
50%