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
conversational
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -76,7 +76,15 @@ more details, including on how to concatenate multi-part files.
|
|
| 76 |
| Link | Type | Size/GB | Notes |
|
| 77 |
|:-----|:-----|--------:|:------|
|
| 78 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q2_K.gguf) | Q2_K | 15.7 | |
|
|
|
|
|
|
|
|
|
|
| 79 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q4_K_S.gguf) | Q4_K_S | 24.3 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
| 81 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 82 |
types (lower is better):
|
|
|
|
| 76 |
| Link | Type | Size/GB | Notes |
|
| 77 |
|:-----|:-----|--------:|:------|
|
| 78 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q2_K.gguf) | Q2_K | 15.7 | |
|
| 79 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q3_K_S.gguf) | Q3_K_S | 18.5 | |
|
| 80 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q3_K_M.gguf) | Q3_K_M | 20.5 | lower quality |
|
| 81 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q3_K_L.gguf) | Q3_K_L | 22.1 | |
|
| 82 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q4_K_S.gguf) | Q4_K_S | 24.3 | fast, recommended |
|
| 83 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q4_K_M.gguf) | Q4_K_M | 25.8 | fast, recommended |
|
| 84 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q5_K_S.gguf) | Q5_K_S | 29.3 | |
|
| 85 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q5_K_M.gguf) | Q5_K_M | 30.2 | |
|
| 86 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q6_K.gguf) | Q6_K | 34.9 | very good quality |
|
| 87 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV-GGUF/resolve/main/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-IV.Q8_0.gguf) | Q8_0 | 45.2 | fast, best quality |
|
| 88 |
|
| 89 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 90 |
types (lower is better):
|