mradermacher/DeepSeek-R1-STEM-Coder-7B-GGUF overview
About < quantize version: 2 < output tensor quantised: 1 < convert type: hf < vocab type: < tags: < quants: x f16 Q4 K S Q2 K Q8 0 Q6 K Q3 K M Q3 K S Q3 K L Q4…
Runs locally from ~2.81 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| DeepSeek-R1-STEM-Coder-7B.IQ4_XS.gguf | GGUF | GGUF | 3.96 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q2_K.gguf | GGUF | GGUF | 2.81 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q3_K_L.gguf | GGUF | GGUF | 3.81 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q3_K_M.gguf | GGUF | GGUF | 3.55 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q3_K_S.gguf | GGUF | GGUF | 3.25 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q4_K_M.gguf | GGUF | GGUF | 4.36 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q4_K_S.gguf | GGUF | GGUF | 4.15 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q5_K_M.gguf | GGUF | GGUF | 5.07 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q5_K_S.gguf | GGUF | GGUF | 4.95 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q6_K.gguf | GGUF | GGUF | 5.82 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.Q8_0.gguf | GGUF | GGUF | 7.54 GB | Download |
| DeepSeek-R1-STEM-Coder-7B.f16.gguf | GGUF | GGUF | 14.19 GB | Download |
Model Details
| Model ID | mradermacher/DeepSeek-R1-STEM-Coder-7B-GGUF |
|---|---|
| Author | mradermacher |
| Pipeline | — |
| License | — |
| Base model | Anannta/DeepSeek-R1-STEM-Coder-7B |
| Last modified | 2026-07-02T06:04:19.000Z |
Model README
---
base_model: Anannta/DeepSeek-R1-STEM-Coder-7B
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- mergekit
- merge
---
About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/Anannta/DeepSeek-R1-STEM-Coder-7B
<!-- 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/DeepSeek-R1-STEM-Coder-7B-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 | 3.1 | |
| GGUF | Q3_K_S | 3.6 | |
| GGUF | Q3_K_M | 3.9 | lower quality |
| GGUF | Q3_K_L | 4.2 | |
| GGUF | IQ4_XS | 4.3 | |
| GGUF | Q4_K_S | 4.6 | fast, recommended |
| GGUF | Q4_K_M | 4.8 | fast, recommended |
| GGUF | Q5_K_S | 5.4 | |
| GGUF | Q5_K_M | 5.5 | |
| GGUF | Q6_K | 6.4 | very good quality |
| GGUF | Q8_0 | 8.2 | fast, best quality |
| GGUF | f16 | 15.3 | 16 bpw, overkill |
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/DeepSeek-R1-STEM-Coder-7B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models