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
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。
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。
//////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////// Published by request from the Pennyroyal community. This is a ModelOpt NVFP4 conversion of OrcaRouter’s uncensored Qwen3.8 Flash-Next checkpoint—the conversion I use for local agentic work with Pennyroyal/SGLang. I’ve also heard reports from several community members of it outperforming the stock model on agentic tasks, which added to the interest in sharing this working format.
번역 대기 중 · 원문 표시
> [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. **autotrust/GLM5.3-Flash-E192-DGX-Spark is a compact build of zai-org/GLM-5.3-Flash for desktop Blackwell systems like NVIDIA DGX Spark. It's an unofficial derivative.** It keeps 192 of the 288 routed experts in each layer by **Neural Architecture Search (NAS)**, uses NVFP4 for the experts and still activates 18 B parameters per token. The weights take 124 GiB, the smallest in the family: **two DGX Sparks connected by ConnectX-7** get about 62 GiB of weights per node and the most KV room of any build, and a single 180 GB Blackwell GPU (B200/GB200) runs it with 32 GiB of KV cache. The KV cache uses FP8.
번역 대기 중 · 원문 표시
> [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. **autotrust/GLM5.3-Flash-E224-DGX-Spark is a compact build of zai-org/GLM-5.3-Flash for desktop Blackwell systems like NVIDIA DGX Spark. It's an unofficial derivative.** > 🚀 **Deploying on DGX Spark?** A complete, field-tested runbook for > serving this checkpoint on **two ConnectX-7-linked DGX Sparks** > (vLLM 0.31.0, TP=2, fp8 KV cache) is here: > **DEPLOY-2X-DGX-SPARK.md** — network setup, > NCCL/CX7 pitfalls, memory budgeting, ops & troubleshooting, and > measured throughput (15.7 tok/s single-stream, 71.8 tok/s at 8-way > concurrency, both GPUs ≈96% utilized).
번역 대기 중 · 원문 표시
> [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. **autotrust/GLM5.3-Flash-E256-DGX-Spark is a compact build of zai-org/GLM-5.3-Flash for Blackwell systems, from DGX Spark clusters to a single B200. It's an unofficial derivative.** It keeps 256 of the 288 routed experts in each layer by **Neural Architecture Search (NAS)**, uses NVFP4 for the experts and still activates 18 B parameters per token. It's the largest architecture in the family, with the best Chinese, code and vision scores. The KV cache uses FP8.
번역 대기 중 · 원문 표시
A compact build of nvidia/Qwen3.8-Flash-Next-FP4-Local found by **Neural Architecture Search (NAS)** over the routed-expert configuration: it keeps **384 of the 512 routed experts** in every decoder MoE layer and in the MTP layer. Unchanged from the original: - top-10 routing and the shared experts; - attention, the n-gram PLE table, the vision tower and the tokenizer. **Checkpoint format.** The checkpoint keeps NVIDIA's exact format: - Every kept tensor is a byte-for-byte copy: packed NVFP4 weights, CSF-coded E4M3 block scales, global and input scales, MXFP8 linears and the NVFP4 PLE table. - Only the 49 router matrices change: they keep the rows of the experts chosen by the search. - `text_config.num_experts` is 384.
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。
INT8 weight **and** activation (**W8A8**) quantization of **Qwen/Qwen3.8-27B** — a dense hybrid model (GatedDeltaNet linear-attention + periodic full-attention) with a native vision tower and an MTP head. ~30 GB, so it needs two 24 GB cards (tensor-parallel 2) but leaves a comfortable KV cache. Pick this over the INT4-W4A16 build when you want the fastest prefill and have the VRAM; pick INT4 when you want the fastest decode or a single-card fit. The **MTP head is included** (`mtp.safetensors`, bf16) and is listed in `quantization_config.ignore`, so vLLM loads it unquantized and speculative decoding works out of the box. Quantizers silently drop this head — if you re-quantize the base yourself, graft it back or spec-decode will accept 0 %.
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
4-bit weight quantisation of Qwen/Qwen3.8-27B, built so the model fits a single **24 GB** consumer GPU. > Note on the `qwen3_5` tag: Qwen3.8 is implemented with the Qwen3.5 > architecture (`model_type: qwen3_5`, `Qwen3_5ForConditionalGeneration`), so > the Hub derives that family tag automatically — the upstream > `Qwen/Qwen3.8-27B` repo carries it too. This is Qwen **3.8**. Text-only serving reclaims the vision encoder cache (~5k extra KV tokens on a 24 GB card):
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。
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
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.