Downloads · 30 days
583
16% of all-time downloads
John1604/Qwen3-235B-A22B-Thinking-2507-gguf
Qwen3-235B-A22B-Thinking-2507-gguf is a machine learning model from John1604. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Make sure you have enough ram/gpu to run. On the right of model card, you may see the size of each quantized models.
Downloads · 30 days
583
16% of all-time downloads
All-time downloads
3.7K
Public
Repo size
1.1 TB
Likes
1
Public
Click a slice to open those files.
.gguf768 GB · 100%
From the Hugging Face model README
Make sure you have enough ram/gpu to run. On the right of model card, you may see the size of each quantized models.
Qwen3 235B Thinking 2507 has been as good as any LLM in the world. It can also be run in PC and Mac locally even without internet. If it runs on your pc, it is only loyal to one master -- yourself, not the goverments, not openai, google, amazon, nor xAI.
you may choose the quantized type in the download window.
Load the model to the LM Studio.
| Type | Bits | Quality | Description |
|---|---|---|---|
| Q2_K | 2-bit | 🟥 Low | Minimal footprint; only for tests |
| Q3_K_S | 3-bit | 🟧 Low | “Small” variant (less accurate) |
| Q3_K_M | 3-bit | 🟧 Low–Med | “Medium” variant |
| Q4_K_S | 4-bit | 🟨 Med | Small, faster, slightly less quality |
| Q4_K_M | 4-bit | 🟩 Med–High | “Medium” — best 4-bit balance |
| Q6_K | 6-bit | 🟩🟩🟩 Very High | Almost FP16 quality, larger size |
| Q8_0 | 8-bit | 🟩🟩🟩🟩 | Near-lossless baseline |