⚡ 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:
Explore AI models 78
⚡ 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.
⚡ 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:
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。
Basic profile indexed · More details to follow
⚡ 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).
Qwen3.8-27B-APEX-GGUF
mudler⚡ 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.
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。
Basic profile indexed · More details to follow
⚡ 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).
⚡ 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).
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。
⚡ 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.
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。
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。
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。
rfdetr-cpp-base
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-large
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-medium
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-nano
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-seg-2xlarge
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-seg-large
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-seg-medium
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-seg-nano
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-seg-small
mudler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。
Basic profile indexed · More details to follow
rfdetr-cpp-seg-xlarge
mudler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。
Basic profile indexed · More details to follow
No matching models
Adjust provider, category or input/output filters. New models are added continuously.
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.