Update README.md
Browse files
README.md
CHANGED
|
@@ -20,4 +20,51 @@ tags:
|
|
| 20 |
| Model Variant | Link |
|
| 21 |
|--------------|------|
|
| 22 |
| **Qwen3-4B-Thinking-2507-abliterated-GGUF** | [Hugging Face](https://huggingface.co/prithivMLmods/Qwen3-4B-2507-abliterated-GGUF/tree/main/Qwen3-4B-Thinking-2507-abliterated-GGUF) |
|
| 23 |
-
| **Qwen3-4B-Instruct-2507-abliterated-GGUF** | [Hugging Face](https://huggingface.co/prithivMLmods/Qwen3-4B-2507-abliterated-GGUF/tree/main/Qwen3-4B-Instruct-2507-abliterated-GGUF) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
| Model Variant | Link |
|
| 21 |
|--------------|------|
|
| 22 |
| **Qwen3-4B-Thinking-2507-abliterated-GGUF** | [Hugging Face](https://huggingface.co/prithivMLmods/Qwen3-4B-2507-abliterated-GGUF/tree/main/Qwen3-4B-Thinking-2507-abliterated-GGUF) |
|
| 23 |
+
| **Qwen3-4B-Instruct-2507-abliterated-GGUF** | [Hugging Face](https://huggingface.co/prithivMLmods/Qwen3-4B-2507-abliterated-GGUF/tree/main/Qwen3-4B-Instruct-2507-abliterated-GGUF) |
|
| 24 |
+
|
| 25 |
+
# Model Files
|
| 26 |
+
|
| 27 |
+
## Qwen3-4B-Thinking-2507-abliterated
|
| 28 |
+
|
| 29 |
+
| File Name | Size | Quant Type |
|
| 30 |
+
|-----------|------|------------|
|
| 31 |
+
| Qwen3-4B-Thinking-2507-abliterated.BF16.gguf | 8.05 GB | BF16 |
|
| 32 |
+
| Qwen3-4B-Thinking-2507-abliterated.F16.gguf | 8.05 GB | F16 |
|
| 33 |
+
| Qwen3-4B-Thinking-2507-abliterated.F32.gguf | 16.1 GB | F32 |
|
| 34 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q2_K.gguf | 1.67 GB | Q2_K |
|
| 35 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q3_K_L.gguf | 2.24 GB | Q3_K_L |
|
| 36 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q3_K_M.gguf | 2.08 GB | Q3_K_M |
|
| 37 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q3_K_S.gguf | 1.89 GB | Q3_K_S |
|
| 38 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q4_K_M.gguf | 2.5 GB | Q4_K_M |
|
| 39 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q4_K_S.gguf | 2.38 GB | Q4_K_S |
|
| 40 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q5_K_M.gguf | 2.89 GB | Q5_K_M |
|
| 41 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q5_K_S.gguf | 2.82 GB | Q5_K_S |
|
| 42 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q6_K.gguf | 3.31 GB | Q6_K |
|
| 43 |
+
| Qwen3-4B-Thinking-2507-abliterated.Q8_0.gguf | 4.28 GB | Q8_0 |
|
| 44 |
+
|
| 45 |
+
## Qwen3-4B-Instruct-2507-abliterated
|
| 46 |
+
|
| 47 |
+
| File Name | Size | Quant Type |
|
| 48 |
+
|-----------|------|------------|
|
| 49 |
+
| Qwen3-4B-Instruct-2507-abliterated.BF16.gguf | 8.05 GB | BF16 |
|
| 50 |
+
| Qwen3-4B-Instruct-2507-abliterated.F16.gguf | 8.05 GB | F16 |
|
| 51 |
+
| Qwen3-4B-Instruct-2507-abliterated.F32.gguf | 16.1 GB | F32 |
|
| 52 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q2_K.gguf | 1.67 GB | Q2_K |
|
| 53 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q3_K_L.gguf | 2.24 GB | Q3_K_L |
|
| 54 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q3_K_M.gguf | 2.08 GB | Q3_K_M |
|
| 55 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q3_K_S.gguf | 1.89 GB | Q3_K_S |
|
| 56 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q4_K_M.gguf | 2.5 GB | Q4_K_M |
|
| 57 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q4_K_S.gguf | 2.38 GB | Q4_K_S |
|
| 58 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q5_K_M.gguf | 2.89 GB | Q5_K_M |
|
| 59 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q5_K_S.gguf | 2.82 GB | Q5_K_S |
|
| 60 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q6_K.gguf | 3.31 GB | Q6_K |
|
| 61 |
+
| Qwen3-4B-Instruct-2507-abliterated.Q8_0.gguf | 4.28 GB | Q8_0 |
|
| 62 |
+
|
| 63 |
+
## Quants Usage
|
| 64 |
+
|
| 65 |
+
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
| 66 |
+
|
| 67 |
+
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 68 |
+
types (lower is better):
|
| 69 |
+
|
| 70 |
+
|