# Thinking Mode Switching
Qwen3 4B Llamafile
Apache-2.0
Qwen3-4B is the latest generation large language model in the Qwen series, featuring 4B parameters, supporting a 128k context window and over 100 languages, with outstanding performance in reasoning, instruction following, and agent capabilities.
Large Language Model
Q
Mozilla
995
2
Qwen3 235B A22B GGUF
Apache-2.0
Qwen3 is the latest version of the Tongyi Qianwen series of large language models, offering a complete suite of dense models and Mixture of Experts (MoE) models. Based on extensive training data, Qwen3 achieves breakthrough progress in reasoning capabilities, instruction following, agent functionalities, and multilingual support.
Large Language Model
Q
Qwen
1,576
2
Qwen3 235B A22B
Apache-2.0
Qwen3 is the latest generation of large language models in the Qwen series, offering a range of dense and Mixture of Experts (MoE) models. Based on extensive training, Qwen3 has achieved groundbreaking progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model
Transformers

Q
unsloth
421
2
Qwen3 4B GGUF
Apache-2.0
Qwen3 is the latest version of the Tongyi Qianwen series of large language models, offering a range of dense and mixture-of-experts (MoE) models. Based on large-scale training, Qwen3 has achieved breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model
Q
Qwen
4,225
6
Qwen3 14B GPTQ Int4
Apache-2.0
Qwen3-4B is the latest 4-billion-parameter large language model in the Qwen series, supporting switching between thinking and non-thinking modes, with excellent performance in reasoning, multilingual, and agent tasks.
Large Language Model
Transformers

Q
JunHowie
640
2
Qwen3 8B GGUF
Apache-2.0
Qwen3 is the latest generation of large language models in the Tongyi Qianwen series, offering a complete suite of dense models and mixture-of-experts (MoE) models. Based on large-scale training, Qwen3 achieves breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model
Transformers

Q
Mungert
1,931
7
Qwen3 32B GPTQ Int4
Apache-2.0
Qwen3 is the latest 8B parameter version of the Tongyi Qianwen series large language model, supporting thinking mode switching, multilingual processing, and tool invocation, with powerful reasoning and dialogue capabilities.
Large Language Model
Transformers

Q
JunHowie
1,079
3
Qwen3 14B 128K GGUF
Apache-2.0
Qwen3 is the latest generation of large language models in the Qwen series, offering a range of dense and mixture-of-experts (MoE) models. Based on extensive training, Qwen3 has achieved breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model English
Q
unsloth
10.20k
13
Qwen3 30B A3B 128K GGUF
Apache-2.0
Qwen3 is the latest generation of large language models in the Tongyi Qianwen series, offering a complete system of dense and mixture-of-experts (MoE) models. Based on extensive training, Qwen3 achieves breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model English
Q
unsloth
48.68k
43
Qwen3 8B 128K GGUF
Apache-2.0
Qwen3 is the latest 8B-parameter version in the Tongyi Qianwen series of large language models, supporting switching between thinking and non-thinking modes, featuring 128K context length and exceptional multilingual capabilities.
Large Language Model English
Q
unsloth
15.29k
14
Qwen3 235B A22B 128K GGUF
Apache-2.0
Qwen3 is the latest generation large language model in the Tongyi Qianwen series, offering a complete suite of dense and Mixture of Experts (MoE) models. Based on large-scale training, Qwen3 has achieved breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model English
Q
unsloth
310.66k
26
Qwen3 235B A22B FP8
Apache-2.0
Qwen3 is the latest version of the Tongyi Qianwen series of large language models, offering a complete suite of dense models and Mixture of Experts (MoE) models. Based on large-scale training, Qwen3 achieves breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model
Transformers

Q
Qwen
47.30k
68
Qwen3 8B FP8
Apache-2.0
Qwen3-8B-FP8 is the latest version in the Qwen series of large language models, offering FP8 quantization, seamless switching between thinking and non-thinking modes, and powerful reasoning capabilities with multilingual support.
Large Language Model
Transformers

Q
Qwen
22.18k
27
Qwen3 1.7B FP8
Apache-2.0
Qwen3-1.7B-FP8 is the FP8 version of the latest generation of the Qwen series of large language models, with powerful inference, instruction-following, agent interaction, and multilingual support capabilities.
Large Language Model
Transformers

Q
Qwen
5,645
26
Qwen3 1.7B GGUF
Apache-2.0
Qwen3-1.7B is the latest generation of the Qwen series with 1.7B parameters, supporting switching between thinking and non-thinking modes, featuring enhanced reasoning capabilities and multilingual support.
Large Language Model English
Q
unsloth
28.55k
16
Qwen3 0.6B Unsloth Bnb 4bit
Apache-2.0
Qwen3 is the latest generation of the Qwen series large language model, offering a comprehensive set of dense and mixture-of-experts (MoE) models. Based on extensive training, Qwen3 achieves groundbreaking progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model
Transformers English

Q
unsloth
50.36k
7
Qwen3 32B GGUF
Apache-2.0
Qwen3 is the latest version of Alibaba Cloud's large-scale language model series, featuring exceptional reasoning, instruction-following, and multilingual support capabilities. The 32B version is one of its dense models, supporting switching between thinking and non-thinking modes.
Large Language Model English
Q
unsloth
123.35k
57
Qwen3 4B Unsloth Bnb 4bit
Apache-2.0
Qwen3-4B is the latest generation of the Qwen series large language model, featuring 4B parameters and supporting over 100 languages, with outstanding performance in reasoning, instruction following, and agent capabilities.
Large Language Model
Transformers English

Q
unsloth
72.86k
5
Qwen3 4B GGUF
Apache-2.0
Qwen3-4B is the latest generation large language model in the Qwen series with 4B parameters, supporting over 100 languages and demonstrating exceptional reasoning, instruction following, and agent capabilities.
Large Language Model English
Q
unsloth
59.40k
32
Qwen3 32B
Apache-2.0
Qwen3 is the latest generation of large language models in the Tongyi Qianwen series, offering a complete combination of dense models and Mixture-of-Experts (MoE) models. Based on large-scale training, Qwen3 achieves breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.
Large Language Model
Transformers

Q
Qwen
502.01k
321
Qwen3 8B
Apache-2.0
Qwen3 is the latest 8B-parameter version in the Tongyi Qianwen series of large language models, supporting seamless switching between thinking and non-thinking modes with powerful reasoning, instruction following, and agent capabilities.
Large Language Model
Transformers

Q
Qwen
550.09k
294
Featured Recommended AI Models