profile.json

{
  "model_id": "Qwen/Qwen3.5-35B-A3B-Base",
  "revision": "0f0813072d2358973511097385626f21fcb6d422",
  "gguf_repo": "mradermacher/Qwen3.5-35B-A3B-Base-i1-GGUF",
  "gguf_revision": "b7c56547560d3a584780bb471e41449fed4c6446",
  "gguf_file": "Qwen3.5-35B-A3B-Base.i1-Q4_K_M.gguf",
  "quantization": "Published imatrix GGUF i1-Q4_K_M; no requantization",
  "backend": "llama-cpp-python-0.3.35-cu130",
  "inference": "single-token-eot-fresh-cache-v1",
  "prefix_token_id": 248044,
  "cdf": "rounded-logits-64-full-vocabulary-24bit-v1",
  "n_ctx": 16384,
  "n_batch": 1,
  "n_ubatch": 1,
  "flash_attn": false,
  "cache_dtype": "bf16",
  "gguf_sha256": "0c90bd1bbdbfa96937c8f7434f6604688584552e7500203a9aa223f4c07d37d3",
  "gguf_bytes": 21169117824
}