Update README.md
Browse files
README.md
CHANGED
|
@@ -19,4 +19,56 @@ datasets:
|
|
| 19 |
|
| 20 |
# **jupyter-agent-qwen3-4b-AIO-GGUF**
|
| 21 |
|
| 22 |
-
> [Jupyter-agent-qwen3-4b-instruct and jupyter-agent-qwen3-4b-thinking](https://huggingface.co/collections/jupyter-agent/jupyter-agent-68c18c9139c6ba3310ed6067) are specialized 4B-parameter models built on Qwen3-4B for agentic reasoning and data science tasks in Jupyter notebooks, supporting both general instruction following and step-by-step, notebook-native logical analysis. The instruct variant excels at delivering fast, efficient responses without generating detailed reasoning traces, while the thinking variant provides comprehensive intermediate computations and analysis, including tool calling and dataset-grounded reasoning on realistic Kaggle workflows, making both models state-of-the-art for code execution, data exploration, and practical problem solving in Python and multi-turn notebook environments.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
# **jupyter-agent-qwen3-4b-AIO-GGUF**
|
| 21 |
|
| 22 |
+
> [Jupyter-agent-qwen3-4b-instruct and jupyter-agent-qwen3-4b-thinking](https://huggingface.co/collections/jupyter-agent/jupyter-agent-68c18c9139c6ba3310ed6067) are specialized 4B-parameter models built on Qwen3-4B for agentic reasoning and data science tasks in Jupyter notebooks, supporting both general instruction following and step-by-step, notebook-native logical analysis. The instruct variant excels at delivering fast, efficient responses without generating detailed reasoning traces, while the thinking variant provides comprehensive intermediate computations and analysis, including tool calling and dataset-grounded reasoning on realistic Kaggle workflows, making both models state-of-the-art for code execution, data exploration, and practical problem solving in Python and multi-turn notebook environments.
|
| 23 |
+
|
| 24 |
+
| Model Name | Download Link |
|
| 25 |
+
|------------------------------------------|-----------------------------------------------------------------------------------------------|
|
| 26 |
+
| **jupyter-agent-qwen3-4b-instruct-GGUF** | [Link](https://huggingface.co/prithivMLmods/jupyter-agent-qwen3-4b-AIO-GGUF/tree/main) |
|
| 27 |
+
| **jupyter-agent-qwen3-4b-thinking-GGUF** | [Link](https://huggingface.co/prithivMLmods/jupyter-agent-qwen3-4b-AIO-GGUF/tree/main/jupyter-agent-qwen3-4b-thinking) |
|
| 28 |
+
|
| 29 |
+
## Model Files
|
| 30 |
+
|
| 31 |
+
### jupyter-agent-qwen3-4b-instruct-GGUF
|
| 32 |
+
|
| 33 |
+
| File Name | Quant Type | File Size |
|
| 34 |
+
| - | - | - |
|
| 35 |
+
| jupyter-agent-qwen3-4b-instruct.BF16.gguf | BF16 | 8.05 GB |
|
| 36 |
+
| jupyter-agent-qwen3-4b-instruct.F16.gguf | F16 | 8.05 GB |
|
| 37 |
+
| jupyter-agent-qwen3-4b-instruct.F32.gguf | F32 | 16.1 GB |
|
| 38 |
+
| jupyter-agent-qwen3-4b-instruct.Q2_K.gguf | Q2_K | 1.67 GB |
|
| 39 |
+
| jupyter-agent-qwen3-4b-instruct.Q3_K_L.gguf | Q3_K_L | 2.24 GB |
|
| 40 |
+
| jupyter-agent-qwen3-4b-instruct.Q3_K_M.gguf | Q3_K_M | 2.08 GB |
|
| 41 |
+
| jupyter-agent-qwen3-4b-instruct.Q3_K_S.gguf | Q3_K_S | 1.89 GB |
|
| 42 |
+
| jupyter-agent-qwen3-4b-instruct.Q4_K_M.gguf | Q4_K_M | 2.5 GB |
|
| 43 |
+
| jupyter-agent-qwen3-4b-instruct.Q4_K_S.gguf | Q4_K_S | 2.38 GB |
|
| 44 |
+
| jupyter-agent-qwen3-4b-instruct.Q5_K_M.gguf | Q5_K_M | 2.89 GB |
|
| 45 |
+
| jupyter-agent-qwen3-4b-instruct.Q5_K_S.gguf | Q5_K_S | 2.82 GB |
|
| 46 |
+
| jupyter-agent-qwen3-4b-instruct.Q6_K.gguf | Q6_K | 3.31 GB |
|
| 47 |
+
| jupyter-agent-qwen3-4b-instruct.Q8_0.gguf | Q8_0 | 4.28 GB |
|
| 48 |
+
|
| 49 |
+
### jupyter-agent-qwen3-4b-thinking-GGUF
|
| 50 |
+
|
| 51 |
+
| File Name | Quant Type | File Size |
|
| 52 |
+
| - | - | - |
|
| 53 |
+
| jupyter-agent-qwen3-4b-thinking.BF16.gguf | BF16 | 8.05 GB |
|
| 54 |
+
| jupyter-agent-qwen3-4b-thinking.F16.gguf | F16 | 8.05 GB |
|
| 55 |
+
| jupyter-agent-qwen3-4b-thinking.F32.gguf | F32 | 16.1 GB |
|
| 56 |
+
| jupyter-agent-qwen3-4b-thinking.Q2_K.gguf | Q2_K | 1.67 GB |
|
| 57 |
+
| jupyter-agent-qwen3-4b-thinking.Q3_K_L.gguf | Q3_K_L | 2.24 GB |
|
| 58 |
+
| jupyter-agent-qwen3-4b-thinking.Q3_K_M.gguf | Q3_K_M | 2.08 GB |
|
| 59 |
+
| jupyter-agent-qwen3-4b-thinking.Q3_K_S.gguf | Q3_K_S | 1.89 GB |
|
| 60 |
+
| jupyter-agent-qwen3-4b-thinking.Q4_K_M.gguf | Q4_K_M | 2.5 GB |
|
| 61 |
+
| jupyter-agent-qwen3-4b-thinking.Q4_K_S.gguf | Q4_K_S | 2.38 GB |
|
| 62 |
+
| jupyter-agent-qwen3-4b-thinking.Q5_K_M.gguf | Q5_K_M | 2.89 GB |
|
| 63 |
+
| jupyter-agent-qwen3-4b-thinking.Q5_K_S.gguf | Q5_K_S | 2.82 GB |
|
| 64 |
+
| jupyter-agent-qwen3-4b-thinking.Q6_K.gguf | Q6_K | 3.31 GB |
|
| 65 |
+
| jupyter-agent-qwen3-4b-thinking.Q8_0.gguf | Q8_0 | 4.28 GB |
|
| 66 |
+
|
| 67 |
+
## Quants Usage
|
| 68 |
+
|
| 69 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 70 |
+
|
| 71 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 72 |
+
types (lower is better):
|
| 73 |
+
|
| 74 |
+
|