You can deploy this model and start earning money today!

robinshao/
safe_huihui_qwen3_5_4b_mxfp4_gguf

Name: safe_huihui_qwen3_5_4b_mxfp4_gguf
Availability: InStock

gguf

endpoints_compatible

conversational

Views

No views yet

robinshao/safe_huihui_qwen3_5_4b_mxfp4_gguf

Source model: robinshao/safe_huihui_qwen3_5_4b

This repo contains:

safe_huihui_qwen3_5_4b_mxfp4_gguf.gguf: GGUF produced with the local patched llama.cpp toolchain
llama.cpp.src-patched.zip: current uncompiled patched source tree
llama.cpp.build-local-bin.zip: compiled binaries matching the source tree
llama.cpp.build-windows-cuda-local-bin.zip: additional compiled patched llama.cpp binaries
build_result.json: build, quantization, and smoke-test summary

Quantization summary:

json

{
  "arch": "qwen35",
  "tensor_count": 426,
  "type_counts": {
    "Q8_0": 1,
    "F32": 177,
    "MXFP4": 248
  },
  "converted_preview": [
    {
      "index": 1,
      "name": "token_embd.weight",
      "from": "BF16",
      "to": "Q8_0",
      "bytes": 675430400
    },
    {
      "index": 2,
      "name": "blk.0.attn_norm.weight",
      "from": "F32",
      "to": "F32",
      "bytes": 10240
    },
    {
      "index": 3,
      "name": "blk.0.ssm_a",
      "from": "F32",
      "to": "F32",
      "bytes": 128
    },
    {
      "index": 4,
      "name": "blk.0.ssm_conv1d.weight",
      "from": "F32",
      "to": "F32",
      "bytes": 131072
    },
    {
      "index": 5,
      "name": "blk.0.ssm_dt.bias",
      "from": "F32",
      "to": "F32",
      "bytes": 128
    },
    {
      "index": 6,
      "name": "blk.0.ssm_alpha.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 43520
    },
    {
      "index": 7,
      "name": "blk.0.ssm_beta.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 43520
    },
    {
      "index": 8,
      "name": "blk.0.attn_qkv.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 11141120
    },
    {
      "index": 9,
      "name": "blk.0.attn_gate.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 5570560
    },
    {
      "index": 10,
      "name": "blk.0.ssm_norm.weight",
      "from": "F32",
      "to": "F32",
      "bytes": 512
    },
    {
      "index": 11,
      "name": "blk.0.ssm_out.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 5570560
    },
    {
      "index": 12,
      "name": "blk.0.ffn_down.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 12533760
    },
    {
      "index": 13,
      "name": "blk.0.ffn_gate.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 12533760
    },
    {
      "index": 14,
      "name": "blk.0.ffn_up.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 12533760
    },
    {
      "index": 15,
      "name": "blk.0.post_attention_norm.weight",
      "from": "F32",
      "to": "F32",
      "bytes": 10240
    },
    {
      "index": 16,
      "name": "blk.1.attn_norm.weight",
      "from": "F32",
      "to": "F32",
      "bytes": 10240
    },
    {
      "index": 17,
      "name": "blk.1.ssm_a",
      "from": "F32",
      "to": "F32",
      "bytes": 128
    },
    {
      "index": 18,
      "name": "blk.1.ssm_conv1d.weight",
      "from": "F32",
      "to": "F32",
      "bytes": 131072
    },
    {
      "index": 19,
      "name": "blk.1.ssm_dt.bias",
      "from": "F32",
      "to": "F32",
      "bytes": 128
    },
    {
      "index": 20,
      "name": "blk.1.ssm_alpha.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 43520
    },
    {
      "index": 21,
      "name": "blk.1.ssm_beta.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 43520
    },
    {
      "index": 22,
      "name": "blk.1.attn_qkv.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 11141120
    },
    {
      "index": 23,
      "name": "blk.1.attn_gate.weight",
      "from": "BF16",
      "to": "MXFP4",
      "bytes": 5570560
    },
    {
      "index": 24,
      "name": "blk.1.ssm_norm.weight",
      "from": "F32",
      "to": "F32",
      "bytes": 512
    }
  ],
  "output_bytes": 2586323264
}

Smoke test summary:

json

{
  "ok": true,
  "returncode": 0,
  "timed_out": false,
  "load_seen": true,
  "elapsed_sec": 3.02,
  "stdout_tail": "\nLoading model... \n\n\n▄▄ ▄▄\n██ ██\n██ ██  ▀▀█▄ ███▄███▄  ▀▀█▄    ▄████ ████▄ ████▄\n██ ██ ▄█▀██ ██ ██ ██ ▄█▀██    ██    ██ ██ ██ ██\n██ ██ ▀█▄██ ██ ██ ██ ▀█▄██ ██ ▀████ ████▀ ████▀\n                                    ██    ██\n                                    ▀▀    ▀▀\n\nbuild      : b0-unknown\nmodel      : robinshao__safe_huihui_qwen3_5_4b-mxfp4.gguf\nmodalities : text\n\navailable commands:\n  /exit or Ctrl+C     stop or exit\n  /regen              regenerate the last response\n  /clear              clear the chat history\n  /read <file>        add a text file\n  /glob <pattern>     add text files using globbing pattern\n\n\n> OK\n\n[Start thinking]\nOkay\n\n[ Prompt: 65.0 t/s | Generation: 1000000.0 t/s ]\n\nExiting...\n",
  "stderr_tail": "warning: no usable GPU found, --gpu-layers option will be ignored\nwarning: one possible reason is that llama.cpp was compiled without GPU support\nwarning: consult docs/build.md for compilation instructions\n",
  "ctx_size": 256,
  "ngl": 0,
  "predict_tokens": 1,
  "timeout_sec": 120,
  "gpu_layers_forced": true,
  "stdout_log": "/data/cz_qwen_mxfp4_work/runs/robinshao__safe_huihui_qwen3_5_4b/smoke_logs/robinshao__safe_huihui_qwen3_5_4b-mxfp4.out.log",
  "stderr_log": "/data/cz_qwen_mxfp4_work/runs/robinshao__safe_huihui_qwen3_5_4b/smoke_logs/robinshao__safe_huihui_qwen3_5_4b-mxfp4.err.log"
}