Qwen3-Embedding-8B-4bit-MLX
huynguyendbs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
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
**Hy-Memory-30B-A3B** is a compact long-term-memory writer model (~3B active parameters) developed by Tencent Hunyuan to execute the write path inside external memory frameworks. It directly replaces the general-purpose LLM inside **Mem0**, **MemOS**, and **Hy-Memory** (covering Chat, Working, and Coding scenarios), deciding what information to retain, how precisely to represent it, and how new evidence should update the persistent memory bank. The model is trained in two stages—Memory On-Policy Distillation (OPD) followed by Attributed Memory Reinforcement Learning—and transfers directly to unseen memory frameworks such as **EverMemOS**. Cross-harness macro-average scores on the fixed 20% benchmark matrix. Each harness score averages six metrics equally; Overall averages the four harnesses equally. EverMemOS is held out from training. Figure 1: Hy-Memory-30B-A3B is trained inside the same deployed harness configurations in both stages. OPD supplies dense teacher supervision on student-written state chains; RL examines the resulting banks, assigns chunk-level credit, and carries the selected bank across windows. In the rollout grid, each cell is the bank after chunk t of rollout i, shaded by its chunk score s_i[t]. Advantages are normalized within each column (dashed: one chunk-level group), so the best rollout can differ from chunk to chunk. The outlined cell is the final bank with the highest sum_t s_i[t], which becomes the parent of the next window.
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
This repository provides GGUF quantizations of Hy-Memory-30B-A3B for efficient local inference with llama.cpp. The releases use **Tencent Hunyuan's Hy-Memory quantization recipe**: imatrix calibration plus MoE-aware mixed precision. Routed experts, which dominate parameter count, can be compressed aggressively, while shared experts, attention, and input/output layers keep higher precision. On the same fixed Mem0 LoCoMo setup, even the **~8 GB** expert-mixed build stays within about **1.5 points** of the strongest Q6_K result (**57.25%** vs **58.78%**), so the quality drop remains small while the file size falls to roughly **one quarter** of Q8_0. All six files passed llama.cpp `--check-tensors`, real no-think generation, and the complete fixed 20% Mem0 LoCoMo evaluation. Each version builds its own memory bank under identical settings. These are single-run scores: they do not claim lossless quantization, and lower-bit variants are not guaranteed to beat higher-bit ones.
번역 대기 중 · 원문 표시
🖥️ Official Website | 💬 GitHub | 🪡 AngelSlim | 📚 Hy-MT2 Report Hy-MT2 is a family of “fast-thinking” multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of which support translation among 33 languages and effectively follow translation instructions in multiple languages. For on-device deployment, AngelSlim 1.25-bit extreme quantization reduces the storage requirement of the 1.8B model to only 440 MB and improves inference speed by 1.5x. Multi-dimensional evaluations show that Hy-MT2 delivers outstanding performance across general, real-world business, domain-specific, and instruction-following translation tasks. The 7B and 30B-A3B models outperform open-source models such as DeepSeek-V4-Pro and Kimi K2.6 in fast-thinking mode, while the lightweight 1.8B model also surpasses mainstream commercial APIs from providers such as Microsoft and Doubao overall. In this release, we also open-source IFMTBench, a benchmark for evaluating translation instruction-following capabilities.
번역 대기 중 · 원문 표시
- Model Introduction - Stronger Agent Capabilities - More Reliable Product Experiences - Benchmark Appendix - News - Model Links - Quickstart - Deployment - vLLM - SGLang - Finetuning - Quantization - License - Contact Us **Hy3** is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. Today, we introduce Hy3, which outperforms similar-size models and rivals flagship open-source models with 2-5x parameters. It also shows significant gains in utility across various products and productivity tasks. Building on Hy3 Preview, we further improved the quality and diversity of post-training data while scaling up RL training. Hy3 shows solid gains across reasoning, agentic, and long-context tasks, competitive with much larger flagship models.
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
The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...
번역 대기 중 · 원문 표시
- Model Introduction - A New Flagship Generation - Built for Productivity - Benchmark Appendix - Known Limitations - News - Model Links - Quickstart - Deployment - vLLM - SGLang - Finetuning - Quantization - License - Contact Us **Hy4 preview** is a new-generation Mixture-of-Experts (MoE) flagship model developed by the Tencent Hy Team. The model comprises 770B total parameters, of which 49B are activated per token. The backbone consists of 78 layers, where the first layer uses a standard dense FFN and the remaining 77 layers replace it with MoE, each containing 256 routed experts and 1 shared expert; every token activates the top-8 routed experts along with the shared expert. In addition to the backbone, 1 native MTP layer (10B total parameters, 0.7B activated) is built in for speculative decoding. On the architecture side, inspired by DeepSeek and GLM, the attention module employs Gated DeepSeek Sparse Attention (Gated DSA) with IndexCache for cross-layer sparse index reuse. The residual pathway uses iHC (identity Hyper-Connections) to expand inter-layer information flow.
번역 대기 중 · 원문 표시
> ### Teacher model > > This model is a **LoRA decision-distillation of > `convaiinnovations/laya`** > by **Convai Innovations**. laya supplies every training label — the > `should_compact` / `preserve` / `level` / `mode` decisions this model emits. > No laya weights are redistributed here; the teacher is credited as the source > of the supervision, which it is. > > If you want the same decisions without this model, go and use laya. A **Qwen3.8-27B Bonsai 2 (Heretic)** derivative carrying a small LoRA that turns a long working context into one structured compaction decision. **Text only.** No vision tower, no projector. If you feed it images it will not do anything useful with them.
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
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
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
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
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
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
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
번역 대기 중 · 원문 표시
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.