DeepSeek-V4.1-Flash-1017-REAP192-GGUF
patrickbdevaney基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
언어부터 이미지, 오픈 웨이트부터 API까지. 기능과 실제 비용을 비교하세요.
다음 아이디어에 맞는 AI를 찾아보세요.
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
**50% expert-pruned `zai-org/GLM-5.3-Flash` (301B → 157B total, 12.5B active) in GGUF (`IQ3_M` to `Q4_K_M`, 72.9–94.8 GiB) with preserved `Q8_0` MLA + Indexer attention.** **GLM-5.3-Flash-REAP50-GGUF** provides single-file GGUF quantizations of `zai-org/GLM-5.3-Flash` compressed with **REAP-50** (Router-weighted Expert Activation Pruning, retaining **128 of 256 routed experts per MoE layer**). Total parameters drop from **301B to 157B** while active parameters per token remain **12.5B** (top-8 of 128 routed experts + 1 shared expert + Multi-head Latent Attention + Dynamic Sparse Attention Indexer), fitting comfortably inside a single **128 GB unified-memory system** (NVIDIA Jetson AGX Thor, DGX Spark, Mac Studio, or Strix Halo) with up to 202K context. - **50% Routed-Expert Compression (301B → 157B Total, 12.5B Active):** Retains 128 of 256 routed experts across all 75 MoE layers (`layers 3..77`) using a 5-pool domain-balanced REAP saliency calibration (`general`, `code`, `math`, `Chinese`, `tool-use`) with union top-16 specialist protection and frequency-floor guards (`f_j >= 40`). - **Two Weight Vintages Disclosed Transparently (`v2` vs `v3`):** - **`Q4_K_M` (94.8 GiB) & `Q3_K_M` (77.3 GiB) are `v3`** (uploaded 2026-10-20): include the **layer-78 MTP draft head** (`nextn.*` tensors) and the **layer-77 shared-expert output-scale correction (`0.7209x`)** that removes high-entropy tail collapse (`kl_full` reduced from `0.506` to `0.388`). - **`Q4_K_S` (90.0 GiB), `IQ4_XS` (85.6 GiB), & `IQ3_M` (72.9 GiB) are `v2`** (uploaded 2026-10-16): 78-layer (`0..77`) builds without the layer-77 shared-expert scale or layer-78 MTP tensors. - **Uncompromised `Q8_0` Attention & DSA Indexer Path:** Every quantization preserves **all MLA (`wq_a`, `wq_b`, `wkv_a_mqa`, `wkv_b`, `wo`), DSA Indexer (`indexer.wq_b`, `indexer.wk`, `indexer.k_norm`, `indexer.weights_proj`), shared experts (`ffn_*_shexp`), and dense layers (`0..2`) at `Q8_0` or `F32`**, quantizing only the routed expert banks (`ffn_gate_exps`, `ffn_up_exps`, `ffn_down_exps`). - **Paired Held-Out Teacher Evaluation (`262,144` Tokens across 64 Prompts × 4,096 Context):** Evaluates directly against the unpruned 301B `zai-org/GLM-5.3-Flash` teacher: `Q4_K_M` achieves **`0.3204` top-32 KL divergence** and **`83.39%` top-1 argmax agreement** (`88.2%` on math, `86.7%` on Chinese, `86.5%` on code).
번역 대기 중 · 원문 표시
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
**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-
번역 대기 중 · 원문 표시
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
제공사, 분류, 입출력 조건을 조정하세요. 새 모델이 계속 등록됩니다.
월간 토큰 사용량으로 예상 API 비용을 비교하세요.
수집된 백만 토큰당 USD 요금입니다. 캐시 할인, 구간 요금, 추가 추론 출력, 세금은 제외됩니다. 최신 요금은 출처에서 확인하세요.
입력, 출력, 캐시 요금을 구분하고 동일 작업량으로 비교하세요. 이미지, 음성, 영상은 개수, 시간, 해상도로 과금될 수 있습니다.
반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 제한, 정책을 확인하세요. 자체 호스팅에는 연산 및 유지 비용도 듭니다.
순위는 작업, 버전, 평가 방식에 따라 다릅니다. 실제 업무로 정확도, 지연, 안정성, 비용을 비교하세요.