dinerburger/qwen3-coder-next-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "base_model": [
      "Qwen/Qwen3-Coder-Next"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "base_model": [
        "Qwen/Qwen3-Coder-Next"
      ]
    },
    "hero_image_url": "",
    "summary": "This is a custom GGUF quantization of Qwen3-Coder-Next, using the unsloth imatrix data with specific focus on retaining quality in embedding, output and attention tensors. IQ4_XS quantization script: `` QUANT=\"IQ4_XS\" llama-quantize \\ --output-tensor-type q8_0 \\ --token-embedding-type q8_0 \\ --tensor-type attn_qkv=bf16 \\ --tensor-type attn_v=bf16 \\ --tensor-type attn_q=bf16 \\ --tensor-type attn_k=bf16 \\ --tensor-type attn_gate=bf16 \\ --tensor-type attn_output=bf16 \\ --tensor-type ssm_ba=bf16 \\ --tensor-type ssm_beta=bf16 \\ --tensor-type ssm_alpha=bf16 \\ --tensor-type ssm_out=bf16 \\ --tensor-type ffn_down_shexp=bf16 \\ --tensor-type ffn_gate_shexp=bf16 \\ --tensor-type ffn_up_shexp=bf16 \\ --tensor-type ffn_down_exps=iq4_nl \\ --imatrix Qwen-Coder-Next-imatrix.gguf_file \\ BF16/Qwen3-Coder-Next-BF16-00001-of-00004.gguf \\ Qwen3-Coder-Next.${QUANT}.gguf \\ ${QUANT} ` IQ3_S quantization script: ` QUANT=\"IQ3_S\" llama-quantize \\ --output-tensor-type q6_k \\ --token-embedding-type q6_k \\ --tensor-type attn_qkv=bf16 \\ --tensor-type attn_v=bf16 \\ --tensor-type attn_q=bf16 \\ --tensor-type attn_k=bf16 \\ --tensor-type attn_gate=bf16 \\ --tensor-type attn_output=bf16 \\ --tensor-type ssm_ba=bf16 \\ --tensor-type ssm_beta=bf16 \\ --tensor-type ssm_alpha=bf16 \\ --tensor-type ssm_out=bf16 \\ --tensor-type ffn_down_shexp=bf16 \\ --tensor-type ffn_gate_shexp=bf16 \\ --tensor-type ffn_up_shexp=bf16 \\ --tensor-type ffn_down_exps=iq4_xs \\ --imatrix Qwen-Coder-Next-imatrix.gguf_file \\ BF16/Qwen3-Coder-Next-BF16-00001-of-00004.gguf \\ Qwen3-Coder-Next.${QUANT}.gguf \\ ${QUANT} ``",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nbase_model:\n- Qwen/Qwen3-Coder-Next\n---\n\nThis is a custom GGUF quantization of [Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next), using the [unsloth imatrix data](https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF/resolve/main/imatrix_unsloth.gguf_file) with specific focus on retaining quality in embedding, output and attention tensors.\n\nIQ4_XS quantization script:\n```\nQUANT=\"IQ4_XS\"\nllama-quantize \\\n  --output-tensor-type q8_0 \\\n  --token-embedding-type q8_0 \\\n  --tensor-type attn_qkv=bf16 \\\n  --tensor-type attn_v=bf16 \\\n  --tensor-type attn_q=bf16 \\\n  --tensor-type attn_k=bf16 \\\n  --tensor-type attn_gate=bf16 \\\n  --tensor-type attn_output=bf16 \\\n  --tensor-type ssm_ba=bf16 \\\n  --tensor-type ssm_beta=bf16 \\\n  --tensor-type ssm_alpha=bf16 \\\n  --tensor-type ssm_out=bf16 \\\n  --tensor-type ffn_down_shexp=bf16 \\\n  --tensor-type ffn_gate_shexp=bf16 \\\n  --tensor-type ffn_up_shexp=bf16 \\\n  --tensor-type ffn_down_exps=iq4_nl \\\n  --imatrix Qwen-Coder-Next-imatrix.gguf_file \\\n  BF16/Qwen3-Coder-Next-BF16-00001-of-00004.gguf \\\n  Qwen3-Coder-Next.${QUANT}.gguf \\\n  ${QUANT}\n```\n\nIQ3_S quantization script:\n```\nQUANT=\"IQ3_S\"\nllama-quantize \\\n  --output-tensor-type q6_k \\\n  --token-embedding-type q6_k \\\n  --tensor-type attn_qkv=bf16 \\\n  --tensor-type attn_v=bf16 \\\n  --tensor-type attn_q=bf16 \\\n  --tensor-type attn_k=bf16 \\\n  --tensor-type attn_gate=bf16 \\\n  --tensor-type attn_output=bf16 \\\n  --tensor-type ssm_ba=bf16 \\\n  --tensor-type ssm_beta=bf16 \\\n  --tensor-type ssm_alpha=bf16 \\\n  --tensor-type ssm_out=bf16 \\\n  --tensor-type ffn_down_shexp=bf16 \\\n  --tensor-type ffn_gate_shexp=bf16 \\\n  --tensor-type ffn_up_shexp=bf16 \\\n  --tensor-type ffn_down_exps=iq4_xs \\\n  --imatrix Qwen-Coder-Next-imatrix.gguf_file \\\n  BF16/Qwen3-Coder-Next-BF16-00001-of-00004.gguf \\\n  Qwen3-Coder-Next.${QUANT}.gguf \\\n  ${QUANT}\n\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "base_model:Qwen/Qwen3-Coder-Next",
    "base_model:quantized:Qwen/Qwen3-Coder-Next",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 10,
  "downloads": 835,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-14T15:09:28.000Z",
  "created_at": "2026-03-12T13:47:30.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69b2c3f22e1af751954b6640",
  "id": "dinerburger/Qwen3-Coder-Next-GGUF",
  "modelId": "dinerburger/Qwen3-Coder-Next-GGUF",
  "sha": "d13a581c2df1578f5b30e94ae709cb83f087f706",
  "createdAt": "2026-03-12T13:47:30.000Z",
  "lastModified": "2026-03-14T15:09:28.000Z",
  "author": "dinerburger",
  "downloads": 835,
  "likes": 10,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 4
}