mradermacher/Proximus-2x7B-v1-GGUF overview
About < quantize version: 2 < output tensor quantised: 1 < convert type: hf < vocab type: < tags: static quants of https://huggingface.co/preemware/Proximus 2x…
Runs locally from ~4.43 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Proximus-2x7B-v1.IQ3_M.gguf | GGUF | GGUF | 5.35 GB | Download |
| Proximus-2x7B-v1.IQ3_S.gguf | GGUF | GGUF | 5.22 GB | Download |
| Proximus-2x7B-v1.IQ3_XS.gguf | GGUF | GGUF | 4.95 GB | Download |
| Proximus-2x7B-v1.IQ4_XS.gguf | GGUF | GGUF | 6.50 GB | Download |
| Proximus-2x7B-v1.Q2_K.gguf | GGUF | GGUF | 4.43 GB | Download |
| Proximus-2x7B-v1.Q3_K_L.gguf | GGUF | GGUF | 6.27 GB | Download |
| Proximus-2x7B-v1.Q3_K_M.gguf | GGUF | GGUF | 5.78 GB | Download |
| Proximus-2x7B-v1.Q3_K_S.gguf | GGUF | GGUF | 5.20 GB | Download |
| Proximus-2x7B-v1.Q4_K_M.gguf | GGUF | GGUF | 7.25 GB | Download |
| Proximus-2x7B-v1.Q4_K_S.gguf | GGUF | GGUF | 6.84 GB | Download |
| Proximus-2x7B-v1.Q5_K_M.gguf | GGUF | GGUF | 8.51 GB | Download |
| Proximus-2x7B-v1.Q5_K_S.gguf | GGUF | GGUF | 8.26 GB | Download |
| Proximus-2x7B-v1.Q6_K.gguf | GGUF | GGUF | 9.84 GB | Download |
| Proximus-2x7B-v1.Q8_0.gguf | GGUF | GGUF | 12.75 GB | Download |
Model Details
| Model ID | mradermacher/Proximus-2x7B-v1-GGUF |
|---|---|
| Author | mradermacher |
| Pipeline | — |
| License | apache-2.0 |
| Base model | preemware/Proximus-2x7B-v1 |
| Last modified | 2026-09-05T05:18:52.000Z |
Model README
---
base_model: preemware/Proximus-2x7B-v1
language:
- en
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- moe
- merge
- mergekit
- lazymergekit
- beowolx/MistralHermes-CodePro-7B-v1
- preemware/Prox-MistralHermes-7B
---
About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/preemware/Proximus-2x7B-v1
<!-- provided-files -->
For a convenient overview and download list, visit our model page for this model.
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Proximus-2x7B-v1-i1-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) 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 | 4.9 | |
| GGUF | IQ3_XS | 5.4 | |
| GGUF | Q3_K_S | 5.7 | |
| GGUF | IQ3_S | 5.7 | beats Q3_K* |
| GGUF | IQ3_M | 5.8 | |
| GGUF | Q3_K_M | 6.3 | lower quality |
| GGUF | Q3_K_L | 6.8 | |
| GGUF | IQ4_XS | 7.1 | |
| GGUF | Q4_K_S | 7.4 | fast, recommended |
| GGUF | Q4_K_M | 7.9 | fast, recommended |
| GGUF | Q5_K_S | 9.0 | |
| GGUF | Q5_K_M | 9.2 | |
| GGUF | Q6_K | 10.7 | very good quality |
| GGUF | Q8_0 | 13.8 | 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.
<!-- end -->
Run mradermacher/Proximus-2x7B-v1-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models