Model Intelligence Sheet
mradermacher/step-3.5-flash-reap-128b-a11b-i1-gguf overview
About weighted/imatrix quants of https://huggingface.co/lkevincc0/Step-3.5-Flash-REAP-128B-A11B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-GGUF
Downloads
1,336
Likes
1
Pipeline
—
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
24 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ1_M.gguf | GGUF | IQ1_M | 25.28 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ1_S.gguf | GGUF | IQ1_S | 22.74 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ2_M.gguf | GGUF | IQ2_M | 36.79 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ2_S.gguf | GGUF | IQ2_S | 33.40 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ2_XS.gguf | GGUF | IQ2_XS | 32.98 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ2_XXS.gguf | GGUF | IQ2_XXS | 29.52 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ3_M.gguf | GGUF | IQ3_M | 49.23 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ3_S.gguf | GGUF | IQ3_S | 48.73 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ3_XS.gguf | GGUF | IQ3_XS | 45.92 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ3_XXS.gguf | GGUF | IQ3_XXS | 43.40 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-IQ4_XS.gguf | GGUF | IQ4_XS | 60.12 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q2_K.gguf | GGUF | Q2_K | 41.19 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q2_K_S.gguf | GGUF | Q2_K_S | 37.79 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q3_K_L.gguf | GGUF | Q3_K_L | 58.48 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q3_K_M.gguf | GGUF | Q3_K_M | 53.75 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q3_K_S.gguf | GGUF | Q3_K_S | 48.71 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q4_0.gguf | GGUF | — | 63.71 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q4_1.gguf | GGUF | — | 70.61 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q4_K_M.gguf | GGUF | Q4_K_M | 67.82 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q4_K_S.gguf | GGUF | Q4_K_S | 63.83 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q5_K_M.gguf | GGUF | Q5_K_M | 79.79 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q5_K_S.gguf | GGUF | Q5_K_S | 77.62 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.i1-Q6_K.gguf | GGUF | Q6_K | 92.51 GB | Download |
| Step-3.5-Flash-REAP-128B-A11B.imatrix.gguf | GGUF | — | 269.84 MB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "lkevincc0/Step-3.5-Flash-REAP-128B-A11B",
"datasets": [
"lkevincc0/glm47-math-code-calibration-1024"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"mradermacher": {
"readme_rev": 1
},
"quantized_by": "mradermacher",
"tags": [
"reap",
"pruning"
],
"frontmatter": {
"base_model": "lkevincc0/Step-3.5-Flash-REAP-128B-A11B",
"datasets": [
"lkevincc0/glm47-math-code-calibration-1024"
],
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"mradermacher": [],
"quantized_by": "mradermacher",
"tags": [
"reap",
"pruning"
]
},
"hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
"summary": "## About weighted/imatrix quants of https://huggingface.co/lkevincc0/Step-3.5-Flash-REAP-128B-A11B ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-GGUF",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: lkevincc0/Step-3.5-Flash-REAP-128B-A11B\ndatasets:\n- lkevincc0/glm47-math-code-calibration-1024\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n readme_rev: 1\nquantized_by: mradermacher\ntags:\n- reap\n- pruning\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type: -->\n<!-- ### tags: nicoboss -->\n<!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->\n<!-- ### quants_skip: -->\n<!-- ### skip_mmproj: -->\nweighted/imatrix quants of https://huggingface.co/lkevincc0/Step-3.5-Flash-REAP-128B-A11B\n\n<!-- provided-files -->\n\n***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Step-3.5-Flash-REAP-128B-A11B-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-GGUF\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.imatrix.gguf) | imatrix | 0.4 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ1_S.gguf) | i1-IQ1_S | 24.5 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ1_M.gguf) | i1-IQ1_M | 27.2 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 31.8 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 35.5 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ2_S.gguf) | i1-IQ2_S | 36.0 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ2_M.gguf) | i1-IQ2_M | 39.6 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 40.7 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q2_K.gguf) | i1-Q2_K | 44.3 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 46.7 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 49.4 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 52.4 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ3_S.gguf) | i1-IQ3_S | 52.4 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ3_M.gguf) | i1-IQ3_M | 53.0 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 57.8 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 62.9 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 64.7 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q4_0.gguf) | i1-Q4_0 | 68.5 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 68.6 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 72.9 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q4_1.gguf) | i1-Q4_1 | 75.9 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 83.4 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 85.8 | |\n| [GGUF](https://huggingface.co/mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF/resolve/main/Step-3.5-Flash-REAP-128B-A11B.i1-Q6_K.gguf) | i1-Q6_K | 99.4 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/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.\n\n<!-- end -->\n",
"related_quantizations": []
},
"tags": [
"transformers",
"gguf",
"reap",
"pruning",
"en",
"dataset:lkevincc0/glm47-math-code-calibration-1024",
"base_model:lkevincc0/Step-3.5-Flash-REAP-128B-A11B",
"base_model:quantized:lkevincc0/Step-3.5-Flash-REAP-128B-A11B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"likes": 1,
"downloads": 1336,
"gated": false,
"private": false,
"last_modified": "2026-03-04T20:00:10.000Z",
"created_at": "2026-03-03T15:24:11.000Z",
"pipeline_tag": "",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "69a6fd1b5e1b3a4cd6e5348e",
"id": "mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF",
"modelId": "mradermacher/Step-3.5-Flash-REAP-128B-A11B-i1-GGUF",
"sha": "5bbde2b6037aa2a157d4c256a55402585a8d55fe",
"createdAt": "2026-03-03T15:24:11.000Z",
"lastModified": "2026-03-04T20:00:10.000Z",
"author": "mradermacher",
"downloads": 1336,
"likes": 1,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "transformers",
"siblings_count": 26
}