README.md

metadata

base_model: DavidAU/Qwen3-42B-A3B-2507-Thinking-TOTAL-RECALL-v2-Medium-MASTER-CODER
language:
  - en
  - fr
  - zh
  - de
library_name: transformers
license: apache-2.0
mradermacher:
  readme_rev: 1
quantized_by: mradermacher
tags:
  - programming
  - code generation
  - code
  - codeqwen
  - programming
  - code generation
  - code
  - codeqwen
  - moe
  - coding
  - coder
  - qwen2
  - chat
  - qwen
  - qwen-coder
  - chat
  - qwen
  - qwen-coder
  - moe
  - Qwen3-30B-A3B-Thinking-2507
  - Qwen3-30B-A3B
  - mixture of experts
  - 128 experts
  - 8 active experts
  - 256k context
  - qwen3
  - finetune
  - brainstorm 20x
  - brainstorm
  - thinking
  - reasoning
  - qwen3_moe

About

weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-42B-A3B-2507-Thinking-TOTAL-RECALL-v2-Medium-MASTER-CODER

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Qwen3-42B-A3B-2507-Thinking-TOTAL-RECALL-v2-Medium-MASTER-CODER-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	0.3	imatrix file (for creating your own qwuants)
GGUF	i1-IQ2_M	14.1
GGUF	i1-Q2_K_S	14.6	very low quality
GGUF	i1-Q2_K	15.7	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	16.5	lower quality
GGUF	i1-IQ3_XS	17.5
GGUF	i1-Q3_K_S	18.5	IQ3_XS probably better
GGUF	i1-IQ3_S	18.5	beats Q3_K*
GGUF	i1-IQ3_M	18.8
GGUF	i1-Q3_K_M	20.5	IQ3_S probably better
GGUF	i1-Q3_K_L	22.1	IQ3_M probably better
GGUF	i1-IQ4_XS	22.8
GGUF	i1-Q4_0	24.2	fast, low quality
GGUF	i1-Q4_K_S	24.3	optimal size/speed/quality
GGUF	i1-Q4_K_M	25.8	fast, recommended
GGUF	i1-Q4_1	26.7
GGUF	i1-Q5_K_S	29.3
GGUF	i1-Q5_K_M	30.2
GGUF	i1-Q6_K	34.9	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.