AI NEWS.ccAIが動く、未来が変わる
♡ 保存済み 0
AIモデルライブラリ/patrickbdevaney/MiMo-V2.6-Flash-REAP50-GGUF
モデル情報

MiMo-V2.6-Flash-REAP50-GGUF

patrickbdevaney · MiMo-V2.6-Flash-REAP50-GGUF

**GGUF quantizations (`MXFP4_MOE` 86.7 GiB, `Q3_K_S` 77.7 GiB, `Q2_K` 64.8 GiB) + multimodal projector (`mmproj`) + 3-layer MTP draft head of 50%-pruned `XiaomiMiMo/MiMo-V2.6-Flash` (315B → 164B total, 11B active).** GGUF quantizations of **`patrickbdevaney/MiMo-V2.6-Flash-REAP50`** — a **50% REAP expert-pruned** derivative of `XiaomiMiMo/MiMo-V2.6-Flash` (**315B → 164B total parameters**, **11B active parameters** per token, **256 → 128 routed experts** per MoE layer across all 59 MoE layers). 1. **`Q3_K_S` and `Q2_K` were quantised with the custom Python/CUDA converter (`scripts/quantize_gguf_variants.py`), not `llama-quantize --imatrix`.** - Because stock `llama.cpp` does not yet support the `mimo2` hybrid-MLA architecture (see Runtime Compatibility below), `llama-quantize` could not be used to produce `Q3_K_S` or `Q2_K`. - Instead, `scripts/quantize_gguf_variants.py` dequantised the `MXFP4_MOE` expert tensors (`blk.*.ffn_{gate,up,down}_exps.weight`) and packed them directly into `GGML_TYPE_Q3_K` (`3.4375 bpw`) and `GGML_TYPE_Q2_K` (`2.625 bpw`) using standard min-max / absmax block scales on GPU. - The file `MiMo-V2.6-Flash-REAP50.imatrix` (`75.8 MiB`, 357 entries) is published in this repository for downstream use once `llama.cpp` lands `mimo2` support, and contains real activation $\mathbb{E}[x^2]$ statistics collected during the 610,304-token REAP calibration pass — **however, those importance weights were NOT used when computing the scales inside the currently uploaded `Q3_K_S.gguf` and `Q2_K.gguf` files.** An earlier bullet on this card described `MiMo-V2.6-Flash-REAP50.imatrix` as "used for Q3_K/Q2_K quantization"; that was inaccurate and has been corrected here. 2. **No post-pruning router or weight "healing" was applied.** - Every surviving expert tensor in `MiMo-V2.6-Flash-REAP50-MXFP4_MOE.gguf` is a lossless repack of the upstream `XiaomiMiMo/MiMo-V2.6-Flash` OCP MXFP4 nibbles and `E8M0` scales, and every router `ffn_gate_inp.weight` (`[128, 4096]`) and `exp_probs_b.bias` (`[128]`) is an exact unmodified slice of the 128 kept experts per layer. 3. **Held-out teacher-vs-student KL / NLL benchmark status: not yet evaluated.** - Unlike `GLM-5.3-Flash-

翻訳待ちのため原文を表示しています。

画像質問応答multimodallicense:apache-2.0
コンテキスト長非公開
入力 → 出力テキスト、画像 → テキスト
モデルウェイト未確認
情報更新日時2026/10/31 02:41:40
OVERVIEW

モデル紹介

**GGUF quantizations (`MXFP4_MOE` 86.7 GiB, `Q3_K_S` 77.7 GiB, `Q2_K` 64.8 GiB) + multimodal projector (`mmproj`) + 3-layer MTP draft head of 50%-pruned `XiaomiMiMo/MiMo-V2.6-Flash` (315B → 164B total, 11B active).** GGUF quantizations of **`patrickbdevaney/MiMo-V2.6-Flash-REAP50`** — a **50% REAP expert-pruned** derivative of `XiaomiMiMo/MiMo-V2.6-Flash` (**315B → 164B total parameters**, **11B active parameters** per token, **256 → 128 routed experts** per MoE layer across all 59 MoE layers). 1. **`Q3_K_S` and `Q2_K` were quantised with the custom Python/CUDA converter (`scripts/quantize_gguf_variants.py`), not `llama-quantize --imatrix`.** - Because stock `llama.cpp` does not yet support the `mimo2` hybrid-MLA architecture (see Runtime Compatibility below), `llama-quantize` could not be used to produce `Q3_K_S` or `Q2_K`. - Instead, `scripts/quantize_gguf_variants.py` dequantised the `MXFP4_MOE` expert tensors (`blk.*.ffn_{gate,up,down}_exps.weight`) and packed them directly into `GGML_TYPE_Q3_K` (`3.4375 bpw`) and `GGML_TYPE_Q2_K` (`2.625 bpw`) using standard min-max / absmax block scales on GPU. - The file `MiMo-V2.6-Flash-REAP50.imatrix` (`75.8 MiB`, 357 entries) is published in this repository for downstream use once `llama.cpp` lands `mimo2` support, and contains real activation $\mathbb{E}[x^2]$ statistics collected during the 610,304-token REAP calibration pass — **however, those importance weights were NOT used when computing the scales inside the currently uploaded `Q3_K_S.gguf` and `Q2_K.gguf` files.** An earlier bullet on this card described `MiMo-V2.6-Flash-REAP50.imatrix` as "used for Q3_K/Q2_K quantization"; that was inaccurate and has been corrected here. 2. **No post-pruning router or weight "healing" was applied.** - Every surviving expert tensor in `MiMo-V2.6-Flash-REAP50-MXFP4_MOE.gguf` is a lossless repack of the upstream `XiaomiMiMo/MiMo-V2.6-Flash` OCP MXFP4 nibbles and `E8M0` scales, and every router `ffn_gate_inp.weight` (`[128, 4096]`) and `exp_probs_b.bias` (`[128]`) is an exact unmodified slice of the 128 kept experts per layer. 3. **Held-out teacher-vs-student KL / NLL benchmark status: not yet evaluated.** - Unlike `GLM-5.3-Flash-

主な特徴

特点摘要待依据来源补齐，不凭模型名称推断能力。

制約と注意点

具体的な制約を判断する出典が不足しています。実際の性能、遅延、データ方針、ライセンス、提供期間を確認してください。

PRICING & COST

出典別料金と費用分析

料金はチャネル・地域・設定によって異なります。各チャネルの料金は個別に表示し、提供元の統一公式料金とは見なしません。

出典・チャネル入力出力課金単位収集日時
確認可能な料金がありません。出典を確認してください。

月額の基本トークン費用を試算

—

試算はキャッシュ割引、段階料金、マルチモーダル追加料金、検索、税金、追加推論出力を含みません。

INDEPENDENT BENCHMARKS

公開評価と実行設定

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

収録済みの全ランキング →

よくある質問

オープンウェイトなら無料で商用利用できますか？

必ずしもそうではありません。バージョン別のライセンス、商用条件、利用方針を確認してください。自前運用には計算資源と保守費用も必要です。

これはリアルタイムの請求料金ですか？

収集日時付きの料金スナップショットです。最新のバージョン、地域、割引、課金方式は各チャネルで確認してください。

出典と追跡記録

huggingface · patrickbdevaney/MiMo-V2.6-Flash-REAP50-GGUF ↗2026/10/31 02:41:40
huggingface · enrich:3baa5314-ce0d-44d4-af60-51d3fe8ef569 ↗2026/10/30 14:36:59

许可证：apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。