Transformers
GGUF
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
Qwen3-Coder-30B-A3B-Instruct
Qwen3-30B-A3B
mixture of experts
128 experts
8 active experts
1 million context
qwen3
finetune
brainstorm 20x
brainstorm
optional thinking
qwen3_moe
unsloth
Merge
imatrix
conversational
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -80,6 +80,7 @@ more details, including on how to concatenate multi-part files.
|
|
| 80 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.imatrix.gguf) | imatrix | 0.3 | imatrix file (for creating your own qwuants) |
|
| 81 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ1_M.gguf) | i1-IQ1_M | 9.8 | mostly desperate |
|
| 82 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.4 | |
|
|
|
|
| 83 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ2_M.gguf) | i1-IQ2_M | 14.1 | |
|
| 84 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q2_K_S.gguf) | i1-Q2_K_S | 14.6 | very low quality |
|
| 85 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q2_K.gguf) | i1-Q2_K | 15.7 | IQ3_XXS probably better |
|
|
@@ -91,6 +92,7 @@ more details, including on how to concatenate multi-part files.
|
|
| 91 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.8 | |
|
| 92 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q4_K_S.gguf) | i1-Q4_K_S | 24.3 | optimal size/speed/quality |
|
| 93 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q4_K_M.gguf) | i1-Q4_K_M | 25.8 | fast, recommended |
|
|
|
|
| 94 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q6_K.gguf) | i1-Q6_K | 34.9 | practically like static Q6_K |
|
| 95 |
|
| 96 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 80 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.imatrix.gguf) | imatrix | 0.3 | imatrix file (for creating your own qwuants) |
|
| 81 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ1_M.gguf) | i1-IQ1_M | 9.8 | mostly desperate |
|
| 82 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.4 | |
|
| 83 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.6 | |
|
| 84 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ2_M.gguf) | i1-IQ2_M | 14.1 | |
|
| 85 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q2_K_S.gguf) | i1-Q2_K_S | 14.6 | very low quality |
|
| 86 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q2_K.gguf) | i1-Q2_K | 15.7 | IQ3_XXS probably better |
|
|
|
|
| 92 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-IQ4_XS.gguf) | i1-IQ4_XS | 22.8 | |
|
| 93 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q4_K_S.gguf) | i1-Q4_K_S | 24.3 | optimal size/speed/quality |
|
| 94 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q4_K_M.gguf) | i1-Q4_K_M | 25.8 | fast, recommended |
|
| 95 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q5_K_S.gguf) | i1-Q5_K_S | 29.3 | |
|
| 96 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V-i1-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-TNG-IV-PKDick-V.i1-Q6_K.gguf) | i1-Q6_K | 34.9 | practically like static Q6_K |
|
| 97 |
|
| 98 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|