aessedai/qwen3.5-122b-a10b-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": [
      "Qwen/Qwen3.5-122B-A10B"
    ],
    "frontmatter": {
      "base_model": [
        "Qwen/Qwen3.5-122B-A10B"
      ]
    },
    "hero_image_url": "kld_data/01_kld_vs_filesize.png \"Chart showing Pareto KLD analysis of quants\"",
    "summary": "## Updates ### 3/10/2026 I've uploaded new quants using the new fused Up + Gate conversion, this offers up to a +10% boost in prompt processing speed from my testing.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model:\n- Qwen/Qwen3.5-122B-A10B\n---\n## Updates\n### 3/10/2026\nI've uploaded new quants using the new fused Up + Gate conversion, this offers up to a +10% boost in prompt processing speed from my testing.\n\n## Description\nThis repo contains specialized MoE-quants for Qwen3.5-122B-A10B. The idea being that given the huge size of the FFN tensors compared to the rest of the tensors in the model, it should be possible to achieve a better quality while keeping the overall size of the entire model smaller compared to a similar naive quantization. To that end, the quantization type default is kept in high quality and the FFN UP + FFN GATE tensors are quanted down along with the FFN DOWN tensors.\n\n| Quant | Size | Mixture | PPL | 1-(Mean PPL(Q)/PPL(base)) | KLD |\n| :--------- | :--------- | :------- | :------- | :------- | :------- |\n| Q5_K_M | 85.26 GiB (6.00 BPW) | Q8_0 / Q5_K / Q5_K / Q6_K | 4.822883 ± 0.028429 | +0.1056% | 0.005545 ± 0.000044 |\n| Q4_K_M | 71.48 GiB (5.03 BPW) | Q8_0 / Q4_K / Q4_K / Q5_K | 4.830384 ± 0.028459 | +0.2613% | 0.010455 ± 0.000084 |\n| IQ4_XS | 56.29 GiB (3.96 BPW) | Q8_0 / IQ3_S / IQ3_S / IQ4_XS | 4.914250 ± 0.028952 | +2.0020% | 0.027787 ± 0.000206 |\n| IQ3_S | 43.39 GiB (3.05 BPW) | Q8_0 / IQ2_S / IQ2_S / IQ3_S | 5.126355 ± 0.030507 | +6.4046% | 0.074562 ± 0.000524 |\n| IQ2_XXS | 31.58 GiB (2.22 BPW) | Q4_K / IQ2_XXS / IQ2_XXS / IQ2_XXS | 5.727638 ± 0.035038 | +18.8850% | 0.185195 ± 0.001112 |\n\n![kld_graph](kld_data/01_kld_vs_filesize.png \"Chart showing Pareto KLD analysis of quants\")\n![ppl_graph](kld_data/02_ppl_vs_filesize.png \"Chart showing Pareto PPL analysis of quants\")",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "base_model:Qwen/Qwen3.5-122B-A10B",
    "base_model:quantized:Qwen/Qwen3.5-122B-A10B",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 42,
  "downloads": 5312,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-13T02:49:21.000Z",
  "created_at": "2026-02-24T17:34:49.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "699de139f9f2dd55f075f303",
  "id": "AesSedai/Qwen3.5-122B-A10B-GGUF",
  "modelId": "AesSedai/Qwen3.5-122B-A10B-GGUF",
  "sha": "9bf9aae2683153d2920fdbb49526b8ccabf1a5a8",
  "createdAt": "2026-02-24T17:34:49.000Z",
  "lastModified": "2026-03-13T02:49:21.000Z",
  "author": "AesSedai",
  "downloads": 5312,
  "likes": 42,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 29
}