サイト内検索

AI モデル 84760

• DeepSeek-V4-Flash-Vision-Exp-MLX↗

  inferencerlabs

• Qwen3.5-9B-int4-AutoRound↗

  Intel

• Qwen3.8-27B-3Bit-GSQ↗

  ISTA-DASLab

• simpletuner-josh-test01↗

  jsterlingvids

• Qwen3.8-Flash-Next-IQ4_XS-GGUF↗

  julianmb

  second-generation quant: same trunk type (iq4_xs), but calibrated with a 926-entry imatrix (1,024 chunks) via the ROCmFPX banded quantizer, and the 51B PLE lookup table **left at q8_0** (no `--tensor-type` cut). 5.56 bpw, 115 giB — 24 giB bigger than the 91g PLE file. pick M2 when you want the **best measured quality** and don't mind the 24 giB: at ≤32k plain it matches PLE, and at 32k MTP it measured fastest. for shallow-depth MTP speed take the 91g PLE; for deep 128k+ MTP the static 116g had a small in-sweep edge (17.4 vs 13.3/13.5 — within the same-config spread, n=1 caveat). every quant descends from an F16 that was byte-verified against the official `Qwen/Qwen3.8-Flash-Next-FP8` checkpoint: hyper-connection norms folded to (1 + w) (97/97 tensors — the converter bug that produces deterministic garbage is fixed in our pipeline), PLE fp8 scale applied, expert stacking identity probed 512x3, GDN v-head reorder checked. details: https://github.com/julianmb/haloq38flash

• LORAs↗

  kukidevalml

• Alif-1.0-8B-Instruct↗

  large-traversaal

• ideogram-4-GGUF↗

  leejet

• Eris_PrimeV4-Vision-32k-7B-GGUF-IQ-Imatrix↗

  Lewdiculous

• Qwen3-235B-A22B-Thinking-2507-MLX-8bit↗

  lmstudio-community