ddh0/q4_k_x.gguf IQ4_XS_X 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
ddh0/q4_k_x.gguf overview
Q4KX.gguf "Q4KX" is an unofficial llama.cpp quantization scheme. The GGUF models available in this repo are quantized as follows: | Tensor name | GGML type | | -------------- | ---------- | | tokenembd | Q4K | | ffngate | Q4K | | ffnup | Q4K | | ffndown | Q5K | | attnk | Q80 | | attnq | Q4K | | attnv | Q80 | | attnoutput | Q5K | | output | Q8_0 |
Downloads
84
Likes
2
Pipeline
—
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
16 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Cassiopeia-70B-Q4_K_X.gguf | GGUF | Q4_K_X | 40.90 GB | Download |
| Diagesis-Q4_K_X.gguf | GGUF | Q4_K_X | 40.90 GB | Download |
| Hunyuan-A13B-Instruct-Q4_K_X.gguf | GGUF | Q4_K_X | 45.38 GB | Download |
| L3.3-Unnamed-Exp-70B-v0.8-Q4_K_X.gguf | GGUF | Q4_K_X | 40.90 GB | Download |
| Llama-3.3-70B-Instruct-Q4_K_X.gguf | GGUF | Q4_K_X | 40.90 GB | Download |
| Llama-3.3-70B-Joyous-Q4_K_X.gguf | GGUF | Q4_K_X | 40.90 GB | Download |
| Llama-3.3-70B-Vulpecula-r1-IQ4_XS_X.gguf | GGUF | IQ4_XS_X | 39.81 GB | Download |
| Magistral-Small-2506-Q4_K_X.gguf | GGUF | Q4_K_X | 13.74 GB | Download |
| Mistral-Small-3.2-24B-Instruct-2506-Q4_K_X.gguf | GGUF | Q4_K_X | 13.74 GB | Download |
| Qwen3-14B-Base-Q4_K_X.gguf | GGUF | Q4_K_X | 8.84 GB | Download |
| Qwen3-14B-Q4_K_X.gguf | GGUF | Q4_K_X | 8.84 GB | Download |
| Qwen3-32B-64K-Q4_K_X.gguf | GGUF | Q4_K_X | 19.13 GB | Download |
| Qwen3-8B-Q4_K_X.gguf | GGUF | Q4_K_X | 5.01 GB | Download |
| StrawberryLemonade-70B-v1.2-Q4_K_X.gguf | GGUF | Q4_K_X | 40.90 GB | Download |
| gemma-3-12b-it-Q4_K_X.gguf | GGUF | Q4_K_X | 6.94 GB | Download |
| gemma-3-12b-pt-Q4_K_X.gguf | GGUF | Q4_K_X | 6.94 GB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "unknown",
"frontmatter": {
"license": "unknown"
},
"hero_image_url": "",
"summary": "# Q4_K_X.gguf \"Q4_K_X\" is an **unofficial** llama.cpp quantization scheme. The GGUF models available in this repo are quantized as follows: | Tensor name | GGML type | | -------------- | ---------- | | token_embd | Q4_K | | **ffn_gate** | **Q4_K** | | **ffn_up** | **Q4_K** | | **ffn_down** | **Q5_K** | | attn_k | Q8_0 | | attn_q | Q4_K | | attn_v | Q8_0 | | attn_output | Q5_K | | output | Q8_0 |",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: unknown\n---\n# Q4_K_X.gguf\n\n\"Q4_K_X\" is an **unofficial** llama.cpp quantization scheme. The GGUF models available in this repo are quantized as follows:\n\n| Tensor name | GGML type |\n| -------------- | ---------- |\n| `token_embd` | `Q4_K` |\n| **`ffn_gate`** | **`Q4_K`** |\n| **`ffn_up`** | **`Q4_K`** |\n| **`ffn_down`** | **`Q5_K`** |\n| `attn_k` | `Q8_0` |\n| `attn_q` | `Q4_K` |\n| `attn_v` | `Q8_0` |\n| `attn_output` | `Q5_K` |\n| `output` | `Q8_0` |\n",
"related_quantizations": []
},
"tags": [
"gguf",
"license:unknown",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"likes": 2,
"downloads": 84,
"gated": false,
"private": false,
"last_modified": "2026-01-03T03:51:27.000Z",
"created_at": "2025-06-24T03:54:34.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "685a217ace005a7824292880",
"id": "ddh0/Q4_K_X.gguf",
"modelId": "ddh0/Q4_K_X.gguf",
"sha": "d7084454a2df95afd2d7bfd982177cd42e7e8194",
"createdAt": "2025-06-24T03:54:34.000Z",
"lastModified": "2026-01-03T03:51:27.000Z",
"author": "ddh0",
"downloads": 84,
"likes": 2,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 18
}