94 lines
3.8 KiB
Markdown
94 lines
3.8 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
base_model:
|
|
- dnotitia/Smoothie-Qwen3-4B
|
|
- dnotitia/Smoothie-Qwen3-0.6B
|
|
- dnotitia/Smoothie-Qwen3-1.7B
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
tags:
|
|
- text-generation-inference
|
|
---
|
|
|
|
# **Smoothie-Qwen3-AIO-GGUF**
|
|
|
|
> Smoothie-Qwen3 models are enhancements of Qwen3 language models, applying post-processing techniques to smooth token distributions and promote balanced, multilingual output, especially across varied Unicode ranges. These models are particularly effective for applications needing reduced language bias and improved representation consistency, maintaining the strong reasoning, coding, and dialogue abilities of Qwen3 while producing more stable and diverse generations.
|
|
|
|
## Model Files
|
|
|
|
### Smoothie-Qwen3-0.6B
|
|
|
|
| File Name | Quant Type | File Size |
|
|
| - | - | - |
|
|
| Smoothie-Qwen3-0.6B.BF16.gguf | BF16 | 1.2 GB |
|
|
| Smoothie-Qwen3-0.6B.F16.gguf | F16 | 1.2 GB |
|
|
| Smoothie-Qwen3-0.6B.F32.gguf | F32 | 2.39 GB |
|
|
| Smoothie-Qwen3-0.6B.Q2_K.gguf | Q2_K | 296 MB |
|
|
| Smoothie-Qwen3-0.6B.Q3_K_L.gguf | Q3_K_L | 368 MB |
|
|
| Smoothie-Qwen3-0.6B.Q3_K_M.gguf | Q3_K_M | 347 MB |
|
|
| Smoothie-Qwen3-0.6B.Q3_K_S.gguf | Q3_K_S | 323 MB |
|
|
| Smoothie-Qwen3-0.6B.Q4_0.gguf | Q4_0 | 382 MB |
|
|
| Smoothie-Qwen3-0.6B.Q4_1.gguf | Q4_1 | 409 MB |
|
|
| Smoothie-Qwen3-0.6B.Q4_K.gguf | Q4_K | 397 MB |
|
|
| Smoothie-Qwen3-0.6B.Q4_K_M.gguf | Q4_K_M | 397 MB |
|
|
| Smoothie-Qwen3-0.6B.Q4_K_S.gguf | Q4_K_S | 383 MB |
|
|
| Smoothie-Qwen3-0.6B.Q5_0.gguf | Q5_0 | 437 MB |
|
|
| Smoothie-Qwen3-0.6B.Q5_1.gguf | Q5_1 | 464 MB |
|
|
| Smoothie-Qwen3-0.6B.Q5_K.gguf | Q5_K | 444 MB |
|
|
| Smoothie-Qwen3-0.6B.Q5_K_M.gguf | Q5_K_M | 444 MB |
|
|
| Smoothie-Qwen3-0.6B.Q5_K_S.gguf | Q5_K_S | 437 MB |
|
|
| Smoothie-Qwen3-0.6B.Q6_K.gguf | Q6_K | 495 MB |
|
|
| Smoothie-Qwen3-0.6B.Q8_0.gguf | Q8_0 | 639 MB |
|
|
|
|
### Smoothie-Qwen3-1.7B
|
|
|
|
| File Name | Quant Type | File Size |
|
|
| - | - | - |
|
|
| Smoothie-Qwen3-1.7B.BF16.gguf | BF16 | 3.45 GB |
|
|
| Smoothie-Qwen3-1.7B.F16.gguf | F16 | 3.45 GB |
|
|
| Smoothie-Qwen3-1.7B.F32.gguf | F32 | 6.89 GB |
|
|
| Smoothie-Qwen3-1.7B.Q2_K.gguf | Q2_K | 778 MB |
|
|
| Smoothie-Qwen3-1.7B.Q3_K_L.gguf | Q3_K_L | 1 GB |
|
|
| Smoothie-Qwen3-1.7B.Q3_K_M.gguf | Q3_K_M | 940 MB |
|
|
| Smoothie-Qwen3-1.7B.Q3_K_S.gguf | Q3_K_S | 867 MB |
|
|
| Smoothie-Qwen3-1.7B.Q4_0.gguf | Q4_0 | 1.05 GB |
|
|
| Smoothie-Qwen3-1.7B.Q4_1.gguf | Q4_1 | 1.14 GB |
|
|
| Smoothie-Qwen3-1.7B.Q4_K.gguf | Q4_K | 1.11 GB |
|
|
| Smoothie-Qwen3-1.7B.Q4_K_M.gguf | Q4_K_M | 1.11 GB |
|
|
| Smoothie-Qwen3-1.7B.Q4_K_S.gguf | Q4_K_S | 1.06 GB |
|
|
| Smoothie-Qwen3-1.7B.Q5_0.gguf | Q5_0 | 1.23 GB |
|
|
| Smoothie-Qwen3-1.7B.Q5_1.gguf | Q5_1 | 1.32 GB |
|
|
| Smoothie-Qwen3-1.7B.Q5_K.gguf | Q5_K | 1.26 GB |
|
|
| Smoothie-Qwen3-1.7B.Q5_K_M.gguf | Q5_K_M | 1.26 GB |
|
|
| Smoothie-Qwen3-1.7B.Q5_K_S.gguf | Q5_K_S | 1.23 GB |
|
|
| Smoothie-Qwen3-1.7B.Q6_K.gguf | Q6_K | 1.42 GB |
|
|
| Smoothie-Qwen3-1.7B.Q8_0.gguf | Q8_0 | 1.83 GB |
|
|
|
|
### Smoothie-Qwen3-4B
|
|
|
|
| File Name | Quant Type | File Size |
|
|
| - | - | - |
|
|
| Smoothie-Qwen3-4B.BF16.gguf | BF16 | 8.05 GB |
|
|
| Smoothie-Qwen3-4B.F16.gguf | F16 | 8.05 GB |
|
|
| Smoothie-Qwen3-4B.F32.gguf | F32 | 16.1 GB |
|
|
| Smoothie-Qwen3-4B.Q2_K.gguf | Q2_K | 1.67 GB |
|
|
| Smoothie-Qwen3-4B.Q3_K_L.gguf | Q3_K_L | 2.24 GB |
|
|
| Smoothie-Qwen3-4B.Q3_K_M.gguf | Q3_K_M | 2.08 GB |
|
|
| Smoothie-Qwen3-4B.Q3_K_S.gguf | Q3_K_S | 1.89 GB |
|
|
| Smoothie-Qwen3-4B.Q4_K_M.gguf | Q4_K_M | 2.5 GB |
|
|
| Smoothie-Qwen3-4B.Q4_K_S.gguf | Q4_K_S | 2.38 GB |
|
|
| Smoothie-Qwen3-4B.Q5_K_M.gguf | Q5_K_M | 2.89 GB |
|
|
| Smoothie-Qwen3-4B.Q5_K_S.gguf | Q5_K_S | 2.82 GB |
|
|
| Smoothie-Qwen3-4B.Q6_K.gguf | Q6_K | 3.31 GB |
|
|
| Smoothie-Qwen3-4B.Q8_0.gguf | Q8_0 | 4.28 GB |
|
|
|
|
## Quants Usage
|
|
|
|
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
|
|
|
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
types (lower is better):
|
|
|
|
 |