base_model: DavidAU/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill
language:
- en
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- 256k context
- Qwen3
- Mixture of Experts
- MOE
- MOE Dense
- 2 experts
- 4Bx12
- All use cases
- bfloat16
- merge
- thinking
- reasoning
- GPT-5.1-High-Reasoning-Distill
- Gemini-3-Pro-Preview-High-Reasoning-Distill
- Claude-4.5-Opus-High-Reasoning-Distill
- Claude-Sonnet-4-Reasoning-Distill
- Kimi-K2-Thinking-Distill
- Gemini-2.5-Flash-Distill
- Gemini-2.5-Flash-Lite-Preview-Distill
- gpt-oss-120b-Distill
- GLM-Flash-4.6-Distill
- Open-R1-Distill
- Command-A-Reasoning-Distill
About
weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | imatrix | 0.1 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 7.1 | for the desperate |
| GGUF | i1-IQ1_M | 7.8 | mostly desperate |
| GGUF | i1-IQ2_XXS | 9.1 | |
| GGUF | i1-IQ2_XS | 10.1 | |
| GGUF | i1-IQ2_S | 10.2 | |
| GGUF | i1-IQ2_M | 11.2 | |
| GGUF | i1-Q2_K_S | 11.6 | very low quality |
| GGUF | i1-Q2_K | 12.5 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 13.1 | lower quality |
| GGUF | i1-IQ3_XS | 13.9 | |
| GGUF | i1-Q3_K_S | 14.7 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 14.7 | beats Q3_K* |
| GGUF | i1-IQ3_M | 14.9 | |
| GGUF | i1-Q3_K_M | 16.3 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 17.6 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 18.1 | |
| GGUF | i1-Q4_0 | 19.2 | fast, low quality |
| GGUF | i1-Q4_K_S | 19.3 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 20.5 | fast, recommended |
| GGUF | i1-Q4_1 | 21.2 | |
| GGUF | i1-Q5_K_S | 23.3 | |
| GGUF | i1-Q5_K_M | 24.0 | |
| GGUF | i1-Q6_K | 27.7 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.