kalle07/glm-4.6v-flash-heretic_r18_k001-gguf Q8_0 GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
kalle07/glm-4.6v-flash-heretic_r18_k001-gguf overview
This is a really uncensored version of zai-org/GLM-4.6V-Flash created with Heretic https://github.com/p-e-w/heretic initial Refusals 92/100 -> now 18 Refusals with KL=0.01 18 sounds like a lot, but I added 30 more refusal_markers, so there may be fewer without them. I also added 17 more bad prompts to the dataset. Since this is a reasoning/thinking model, I suggest that you also adapt the system prompt to your needs. Note: This heretic model is highly uncensored; thus use it with extreme caution and care.
Downloads
153
Likes
1
Pipeline
text-generation
Library
transformers
Visibility
Public
Access
Open
Repository Files & Downloads
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "mit",
"pipeline_tag": "text-generation",
"inference": false,
"library_name": "transformers",
"language": [
"zh",
"en"
],
"tags": [
"GLM",
"abliterated",
"uncensored",
"heretic"
],
"base_model": [
"zai-org/GLM-4.6V-Flash"
],
"frontmatter": {
"license": "mit",
"pipeline_tag": "text-generation",
"inference": "false",
"library_name": "transformers",
"language": [
"zh",
"en"
],
"tags": [
"GLM",
"abliterated",
"uncensored",
"heretic"
],
"base_model": [
"zai-org/GLM-4.6V-Flash"
]
},
"hero_image_url": "",
"summary": "This is a really uncensored version of zai-org/GLM-4.6V-Flash created with Heretic https://github.com/p-e-w/heretic initial Refusals 92/100 -> now 18 Refusals with KL=0.01 18 sounds like a lot, but I added 30 more refusal_markers, so there may be fewer without them. I also added 17 more bad prompts to the dataset. Since this is a reasoning/thinking model, I suggest that you also adapt the system prompt to your needs. Note: This heretic model is highly uncensored; thus use it with extreme caution and care.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: mit\npipeline_tag: text-generation\ninference: false\nlibrary_name: transformers\nlanguage:\n- zh\n- en\ntags:\n- GLM\n- abliterated\n- uncensored\n- heretic\nbase_model:\n- zai-org/GLM-4.6V-Flash\n---\n\nThis is a really uncensored version of [zai-org/GLM-4.6V-Flash](https://huggingface.co/zai-org/GLM-4.6V-Flash) created with Heretic<br>\nhttps://github.com/p-e-w/heretic\n<br><br>\ninitial Refusals 92/100<br>\n-> now 18 Refusals with KL=0.01<br>\n18 sounds like a lot, but I added 30 more refusal_markers, so there may be fewer without them.<br>\nI also added 17 more bad prompts to the dataset.<br>\nSince this is a reasoning/thinking model, I suggest that you also adapt the system prompt to your needs.<br><br>\nNote: This heretic model is highly uncensored; thus use it with extreme caution and care.<br>\n<br>\n<br><br>\n",
"related_quantizations": []
},
"tags": [
"transformers",
"gguf",
"GLM",
"abliterated",
"uncensored",
"heretic",
"text-generation",
"zh",
"en",
"base_model:zai-org/GLM-4.6V-Flash",
"base_model:quantized:zai-org/GLM-4.6V-Flash",
"license:mit",
"region:us",
"conversational"
],
"likes": 1,
"downloads": 153,
"gated": false,
"private": false,
"last_modified": "2026-02-22T19:26:00.000Z",
"created_at": "2026-02-22T13:21:28.000Z",
"pipeline_tag": "text-generation",
"library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "699b02d8c055587af243fc79",
"id": "kalle07/GLM-4.6V-Flash-heretic_R18_K001-gguf",
"modelId": "kalle07/GLM-4.6V-Flash-heretic_R18_K001-gguf",
"sha": "c5368ebe09e37e30ef47594623375dce8b83b4d4",
"createdAt": "2026-02-22T13:21:28.000Z",
"lastModified": "2026-02-22T19:26:00.000Z",
"author": "kalle07",
"downloads": 153,
"likes": 1,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "transformers",
"siblings_count": 4
}