AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/teamblobfish/DeepSeek-V4-Flash-GGUF
MODEL PROFILE · 模型档案

DeepSeek-V4-Flash-GGUF

teamblobfish · DeepSeek-V4-Flash-GGUF

GGUF quantizations of `deepseek-ai/DeepSeek-V4-Flash` for use with the V4-aware llama.cpp fork at `cchuter/llama.cpp` @ `feat/v4-port-cuda`. > 📦 **Required: V4-aware llama.cpp fork.** These quants don't load on upstream `ggml-org/llama.cpp` — V4 architecture support (compressor decode, hyperconnection, lightning indexer, FP8 KV simulation, NextN heads) lives only in the fork: > > > > Full build + run instructions in Loading below. > 🖥️ **Supported backends: Apple Silicon (Metal), NVIDIA CUDA (Ada/Blackwell), and CPU.** All 5 V4 custom ops (`ggml_dsv4_rope_tail`, `ggml_dsv4_hc_split_sinkhorn`, `ggml_dsv4_hc_weighted_sum`, `ggml_dsv4_hc_expand`, `ggml_dsv4_fp8_kv_quantize`) have Metal kernels AND CUDA kernels in this fork (validated 19/19 on RTX 5090, CUDA 12.8, SM_120 native). The CUDA FP8 path is gated behind `__CUDA_ARCH__ >= 890`; older NVIDIA hardware (Volta/Turing/Ampere) uses a software-emulated FP8 path that builds cleanly under `-DCMAKE_CUDA_ARCHITECTURES=70` but hasn't been runtime-validated yet. **CUDA testers wanted** — file issues at the fork if you hit problems. ROCm / Vulkan / Metal-on-AMD have no V4 kernels and will fail at the first dsv4 op.

译文排队中，当前展示来源原文。

文本生成license:mit
上下文窗口来源未披露
输入 → 输出文本 → 文本
模型权重待核验
档案更新时间2026/10/31 11:17:31
OVERVIEW

模型介绍

GGUF quantizations of `deepseek-ai/DeepSeek-V4-Flash` for use with the V4-aware llama.cpp fork at `cchuter/llama.cpp` @ `feat/v4-port-cuda`. > 📦 **Required: V4-aware llama.cpp fork.** These quants don't load on upstream `ggml-org/llama.cpp` — V4 architecture support (compressor decode, hyperconnection, lightning indexer, FP8 KV simulation, NextN heads) lives only in the fork: > > > > Full build + run instructions in Loading below. > 🖥️ **Supported backends: Apple Silicon (Metal), NVIDIA CUDA (Ada/Blackwell), and CPU.** All 5 V4 custom ops (`ggml_dsv4_rope_tail`, `ggml_dsv4_hc_split_sinkhorn`, `ggml_dsv4_hc_weighted_sum`, `ggml_dsv4_hc_expand`, `ggml_dsv4_fp8_kv_quantize`) have Metal kernels AND CUDA kernels in this fork (validated 19/19 on RTX 5090, CUDA 12.8, SM_120 native). The CUDA FP8 path is gated behind `__CUDA_ARCH__ >= 890`; older NVIDIA hardware (Volta/Turing/Ampere) uses a software-emulated FP8 path that builds cleanly under `-DCMAKE_CUDA_ARCHITECTURES=70` but hasn't been runtime-validated yet. **CUDA testers wanted** — file issues at the fork if you hit problems. ROCm / Vulkan / Metal-on-AMD have no V4 kernels and will fail at the first dsv4 op.

主要特点

特点摘要待依据来源补齐，不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价，不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价，请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用？

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗？

不是实时结算价格，而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

huggingface · teamblobfish/DeepSeek-V4-Flash-GGUF ↗2026/10/30 17:58:25
huggingface · enrich:903e3c01-7a2b-4972-8ef4-8739cf4725e2 ↗2026/10/31 11:17:31

许可证：mit。模型介绍与第三方评测均以原来源的具体版本和方法为准。