⚡ Each donation = another big MoE quantized I host 30+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. **APEX (Adaptive Precision for EXpert Models)** quantizations of hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled, with the **MTP (multi-token prediction) head bundled** for in-the-box self-speculative decoding. These GGUFs bundle the model's **MTP (multi-token prediction) head** alongside the trunk in a single file, courtesy of llama.cpp PR #22673. With a recent llama.cpp (>= commit 255582687) you can enable self-speculative decoding using just this one file — no separate draft model needed:
번역 대기 중 · 원문 표시
분류 준비 중
입력 미확인→ 출력 미확인
⚡ Each donation = another big MoE quantized I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. 🎉 Patreon (Monthly) | ☕ Buy Me a Coffee | ⭐ GitHub Sponsors 💚 Big thanks to Hugging Face for generously donating additional storage, much appreciated.
번역 대기 중 · 원문 표시
분류 준비 중
입력 미확인→ 출력 미확인
⚡ Each donation = another big MoE quantized I host 30+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. **APEX (Adaptive Precision for EXpert Models)** quantizations of lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled, with the **MTP (multi-token prediction) head bundled** for in-the-box self-speculative decoding. These GGUFs bundle the model's **MTP (multi-token prediction) head** alongside the trunk in a single file, courtesy of llama.cpp PR #22673. With a recent llama.cpp (>= commit 255582687) you can enable self-speculative decoding using just this one file — no separate draft model needed:
번역 대기 중 · 원문 표시
분류 준비 중
입력 미확인→ 출력 미확인
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
입력 텍스트→ 출력 텍스트
⚡ Each donation = another big MoE quantized I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. **APEX (Adaptive Precision for EXpert Models)** quantizations of llmfan46/Qwen3.6-35B-A3B-uncensored-heretic. APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient — edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).
번역 대기 중 · 원문 표시
분류 준비 중
입력 미확인→ 출력 미확인
⚡ Each donation = another big model quantized I host 30+ free APEX quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class models, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. Both include the MTP / NextN head as `blk.64`, so speculative decoding runs against the file itself. The head is kept at Q8_0: a drafter that mispredicts the target wastes the speculation, so it does not get compressed with the rest. Needs a recent llama.cpp with `qwen3_5` support. The architecture landed after the model shipped on 2026-08-13, and older builds segfault on load.
번역 대기 중 · 원문 표시
분류 준비 중
입력 미확인→ 출력 미확인
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
분류 준비 중
입력 미확인→ 출력 미확인
⚡ Each donation = another big MoE quantized I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. All measurements on NVIDIA DGX Spark (GB10, 128 GB VRAM). Perplexity on wikitext-2-raw, context 2048. Accuracy benchmarks via llama.cpp (400 tasks). APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient -- edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling -- no Wikipedia).
번역 대기 중 · 원문 표시
분류 준비 중
입력 미확인→ 출력 미확인
⚡ Each donation = another big MoE quantized I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. Benchmarks coming soon. For reference APEX benchmarks on the Qwen3.5-35B-A3B architecture, see mudler/Qwen3.5-35B-A3B-APEX-GGUF. APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient -- edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).
번역 대기 중 · 원문 표시
분류 준비 중
입력 미확인→ 출력 미확인
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。
분류 준비 중
입력 미확인→ 출력 미확인
⚡ Each donation = another big MoE quantized I host 30+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory), enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant. If APEX quants are useful to you, your support directly funds those bigger runs. **APEX (Adaptive Precision for EXpert Models)** quantizations of Jackrong/Qwopus3.6-35B-A3B-Coder — a Qwen3.6-35B-A3B MoE tuned for coding. > This model ships an MTP head — for self-speculative decoding out of the box, see the MTP-bundled repo: mudler/Qwopus3.6-35B-A3B-Coder-APEX-MTP-GGUF.
번역 대기 중 · 원문 표시
분류 준비 중
입력 미확인→ 출력 미확인
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。
분류 준비 중
입력 미확인→ 출력 미확인
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。
분류 준비 중
입력 미확인→ 출력 미확인
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。
분류 준비 중
입력 미확인→ 출력 미확인
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
입력 이미지→ 출력 미확인
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
입력 이미지→ 출력 미확인
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
입력 이미지→ 출력 미확인
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
입력 이미지→ 출력 미확인
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
입력 이미지→ 출력 이미지
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
입력 이미지→ 출력 이미지
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
입력 이미지→ 출력 이미지
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
입력 이미지→ 출력 이미지
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
입력 이미지→ 출력 이미지
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
입력 이미지→ 출력 이미지
