base_model: sequelbox/Qwen3-14B-Esper3Mix
language:
  - en
library_name: transformers
license: apache-2.0
mradermacher:
  readme_rev: 1
quantized_by: mradermacher
tags:
  - mergekit
  - merge
  - esper
  - esper-3
  - dmind
  - dmind-1-mini
  - cobalt
  - cobalt-2
  - grayline
  - valiant
  - valiant-labs
  - qwen
  - qwen-3
  - qwen-3-14b
  - 14b
  - reasoning
  - web3
  - code
  - code-instruct
  - python
  - javascript
  - dev-ops
  - jenkins
  - terraform
  - scripting
  - powershell
  - azure
  - aws
  - gcp
  - cloud
  - problem-solving
  - architect
  - engineer
  - developer
  - creative
  - analytical
  - expert
  - rationality
  - math
  - math-reasoning
  - math-instruct
  - uncensored
  - unfiltered
  - amoral-ai
  - conversational
  - chat
  - instruct
About
static quants of https://huggingface.co/sequelbox/Qwen3-14B-Esper3Mix
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-14B-Esper3Mix-i1-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 | Q2_K | 5.9 | |
| GGUF | Q3_K_S | 6.8 | |
| GGUF | Q3_K_M | 7.4 | lower quality | 
| GGUF | Q3_K_L | 8.0 | |
| GGUF | IQ4_XS | 8.3 | |
| GGUF | Q4_K_S | 8.7 | fast, recommended | 
| GGUF | Q4_K_M | 9.1 | fast, recommended | 
| GGUF | Q5_K_S | 10.4 | |
| GGUF | Q5_K_M | 10.6 | |
| GGUF | Q6_K | 12.2 | very good quality | 
| GGUF | Q8_0 | 15.8 | fast, best quality | 
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.
