mradermacher/trixster-moe-14b-a8b-v1-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "OccultAI/Trixster-MoE-14B-A8B-v1",
    "datasets": [
      "cgato/SlimOrcaDedupCleaned",
      "Doctor-Shotgun/no-robots-sharegpt",
      "grimulkan/LimaRP-augmented",
      "lemonilia/LimaRP",
      "Locutusque/hercules-v5.0",
      "mlabonne/orpo-dpo-mix-40k",
      "mpasila/LimaRP-augmented-8k-context",
      "NobodyExistsOnTheInternet/PIPPAsharegptv2test",
      "NobodyExistsOnTheInternet/ToxicQAFinal",
      "OccultAI/Morpheus_665",
      "Gryphe/Opus-WritingPrompts",
      "ResplendentAI/NSFW_RP_Format_DPO",
      "Sao10K/c2-Logs-Filtered",
      "Sao10K/Claude-3-Opus-Instruct-15K",
      "Sao10K/Short-Storygen-v2",
      "Setiaku/Stheno-v3.4-Instruct",
      "Setiaku/Stheno-3.4-Creative-2",
      "SicariusSicariiStuff/UBW_Tapestries",
      "Squish42/bluemoon-fandom-1-1-rp-cleaned",
      "teknium/OpenHermes-2.5",
      "Undi95/Capybara-ShareGPT",
      "Undi95/toxic-dpo-v0.1-sharegpt"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "merge",
      "llama",
      "occult",
      "uncensored",
      "moe_karcher"
    ],
    "frontmatter": {
      "base_model": "OccultAI/Trixster-MoE-14B-A8B-v1",
      "datasets": [
        "cgato/SlimOrcaDedupCleaned",
        "Doctor-Shotgun/no-robots-sharegpt",
        "grimulkan/LimaRP-augmented",
        "lemonilia/LimaRP",
        "Locutusque/hercules-v5.0",
        "mlabonne/orpo-dpo-mix-40k",
        "mpasila/LimaRP-augmented-8k-context",
        "NobodyExistsOnTheInternet/PIPPAsharegptv2test",
        "NobodyExistsOnTheInternet/ToxicQAFinal",
        "OccultAI/Morpheus_665",
        "Gryphe/Opus-WritingPrompts",
        "ResplendentAI/NSFW_RP_Format_DPO",
        "Sao10K/c2-Logs-Filtered",
        "Sao10K/Claude-3-Opus-Instruct-15K",
        "Sao10K/Short-Storygen-v2",
        "Setiaku/Stheno-v3.4-Instruct",
        "Setiaku/Stheno-3.4-Creative-2",
        "SicariusSicariiStuff/UBW_Tapestries",
        "Squish42/bluemoon-fandom-1-1-rp-cleaned",
        "teknium/OpenHermes-2.5",
        "Undi95/Capybara-ShareGPT",
        "Undi95/toxic-dpo-v0.1-sharegpt"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "merge",
        "llama",
        "occult",
        "uncensored",
        "moe_karcher"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/OccultAI/Trixster-MoE-14B-A8B-v1  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: OccultAI/Trixster-MoE-14B-A8B-v1\ndatasets:\n- cgato/SlimOrcaDedupCleaned\n- Doctor-Shotgun/no-robots-sharegpt\n- grimulkan/LimaRP-augmented\n- lemonilia/LimaRP\n- Locutusque/hercules-v5.0\n- mlabonne/orpo-dpo-mix-40k\n- mpasila/LimaRP-augmented-8k-context\n- NobodyExistsOnTheInternet/PIPPAsharegptv2test\n- NobodyExistsOnTheInternet/ToxicQAFinal\n- OccultAI/Morpheus_665\n- Gryphe/Opus-WritingPrompts\n- ResplendentAI/NSFW_RP_Format_DPO\n- Sao10K/c2-Logs-Filtered\n- Sao10K/Claude-3-Opus-Instruct-15K\n- Sao10K/Short-Storygen-v2\n- Setiaku/Stheno-v3.4-Instruct\n- Setiaku/Stheno-3.4-Creative-2\n- SicariusSicariiStuff/UBW_Tapestries\n- Squish42/bluemoon-fandom-1-1-rp-cleaned\n- teknium/OpenHermes-2.5\n- Undi95/Capybara-ShareGPT\n- Undi95/toxic-dpo-v0.1-sharegpt\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- merge\n- llama\n- occult\n- uncensored\n- moe_karcher\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/OccultAI/Trixster-MoE-14B-A8B-v1\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#Trixster-MoE-14B-A8B-v1-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-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/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 3.3 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 3.5 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 4.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 4.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.0 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q2_K.gguf) | i1-Q2_K | 5.3 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.5 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.2 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 6.2 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 6.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.8 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.3 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.0 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q4_0.gguf) | i1-Q4_0 | 8.0 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.0 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.4 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q4_1.gguf) | i1-Q4_1 | 8.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF/resolve/main/Trixster-MoE-14B-A8B-v1.i1-Q6_K.gguf) | i1-Q6_K | 11.3 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\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",
    "merge",
    "llama",
    "occult",
    "uncensored",
    "moe_karcher",
    "en",
    "dataset:cgato/SlimOrcaDedupCleaned",
    "dataset:Doctor-Shotgun/no-robots-sharegpt",
    "dataset:grimulkan/LimaRP-augmented",
    "dataset:lemonilia/LimaRP",
    "dataset:Locutusque/hercules-v5.0",
    "dataset:mlabonne/orpo-dpo-mix-40k",
    "dataset:mpasila/LimaRP-augmented-8k-context",
    "dataset:NobodyExistsOnTheInternet/PIPPAsharegptv2test",
    "dataset:NobodyExistsOnTheInternet/ToxicQAFinal",
    "dataset:OccultAI/Morpheus_665",
    "dataset:Gryphe/Opus-WritingPrompts",
    "dataset:ResplendentAI/NSFW_RP_Format_DPO",
    "dataset:Sao10K/c2-Logs-Filtered",
    "dataset:Sao10K/Claude-3-Opus-Instruct-15K",
    "dataset:Sao10K/Short-Storygen-v2",
    "dataset:Setiaku/Stheno-v3.4-Instruct",
    "dataset:Setiaku/Stheno-3.4-Creative-2",
    "dataset:SicariusSicariiStuff/UBW_Tapestries",
    "dataset:Squish42/bluemoon-fandom-1-1-rp-cleaned",
    "dataset:teknium/OpenHermes-2.5",
    "dataset:Undi95/Capybara-ShareGPT",
    "dataset:Undi95/toxic-dpo-v0.1-sharegpt",
    "base_model:OccultAI/Trixster-MoE-14B-A8B-v1",
    "base_model:quantized:OccultAI/Trixster-MoE-14B-A8B-v1",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 2,
  "downloads": 215,
  "gated": false,
  "private": false,
  "last_modified": "2026-02-22T09:00:13.000Z",
  "created_at": "2026-02-22T07:13:04.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "699aac803ccabf2d242bad8a",
  "id": "mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF",
  "modelId": "mradermacher/Trixster-MoE-14B-A8B-v1-i1-GGUF",
  "sha": "28d6b0537bf1294bb07abcae79fbd5d95bacbd59",
  "createdAt": "2026-02-22T07:13:04.000Z",
  "lastModified": "2026-02-22T09:00:13.000Z",
  "author": "mradermacher",
  "downloads": 215,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}