qwen 128 · Ollama

qwen2.5

Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.

tools 0.5b 1.5b 3b 7b 14b 32b 72b

32.2M Pulls 133 Tags Updated 1 year ago

nahiyananwar/mental-health-ai

Compassionate mental health support AI fine-tuned from Qwen 3 (14B) with 128K context.

16 Pulls 1 Tag Updated 3 days ago

mdq100/qwen3.5

Custom Qwen3.5 variants optimized for 128GB unified memory systems, such as AMD Ryzen AI Max+ 395. On Windows 11, GPU is limited to 96GB (32GB reserved for OS/CPU), requiring context window capped at 131072 tokens (128K) to fit within GPU memory limits.

vision tools thinking

320 Pulls 2 Tags Updated 2 months ago

Omoeba/qwen3-coder-128k

tools support and a 128k context length by default

tools 30b

1,292 Pulls 1 Tag Updated 8 months ago

Omoeba/qwen3-2507-abliterated-128k

128k context length for coding and other long-form questions

tools 30b

547 Pulls 1 Tag Updated 10 months ago

lsm03624/Qwen3-30B-A3B-128K-UD-Q8_K_XL

这是unsloth的Q8动态量化版本，精度第一的量化版本！Unsloth Dynamic 2.0 实现了卓越的准确性，并超越了其他领先的量化模型。

tools thinking

258 Pulls 1 Tag Updated 11 months ago

Omoeba/qwen3-2507-thinking-128k

qwen3-2507 with thinking enabled and a default context length of 128k

tools thinking 30b

41 Pulls 1 Tag Updated 10 months ago

mbenhamd/qwen2.5-7b-instruct-cline-128k-q8_0

Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual capabilities. The following model is specialized on Cline (previously Claude-dev)

tools

1,282 Pulls 1 Tag Updated 1 year ago

lsm03624/Qwen3-32B-128K-UD-Q4_K_XL

这是unsloth的Q4动态量化版本，精度第一的量化版本！Unsloth Dynamic 2.0 实现了卓越的准确性，并超越了其他领先的量化模型。

tools

725 Pulls 1 Tag Updated 1 year ago

sammcj/qwen2.5-coder-32b-128k

Qwen2.5 Coder 32B with the corrected 128k context

tools

594 Pulls 1 Tag Updated 1 year ago

mbenhamd/qwen2.5-14b-instruct-cline-128k-q8_0

Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual capabilities. The following model is specialized on Cline (previously Claude-dev)

tools

420 Pulls 1 Tag Updated 1 year ago