JERRYNPC/deepseek-v4.1-flash-nano-v100
text-generation model by JERRYNPC
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
实验版，非官方。 用 REAP 把 DeepSeek-V4.1-Flash-1017 每层 384 个路由专家剪到 80 个，其中 26 个常驻显存、54 个留在宿主内存按需 H2D。目标是让专家不再逐 token 读盘， 把解码稳定在 1 tok/s 以上（32GB 显存 + 64GB 内存）。 (not published yet — only a partial upload landed, so it cannot be run; contact the publisher JERRYNPC if you need the full 384-expert version) 模型目录约 53GB；加 engram 后约 108GB（du 口径约 101GiB）。 专家文件内部按「常驻优先」排序：前 26 个是 residentkeep，启动时装进显存； 后 54 个在宿主 LRU 里，用时通过独立 CUDA 流 H2D。gate 仍是 384 维， expertmask 把 304 个被剪专家置 -inf，keeppos 映射到文件内位置。 engram 是 2 GiB 分片（共 55.3GB），必须先拼回整表，否则启动时查表会报文件不存在： Windows…
Read the full model card ↗ · Preview checked 2026-10-31T12:43:22.670Z
Inside the original model card — Document outline
- DeepSeek-V4.1-nano · 80 experts/layer 单卡实验版
- 仓库组成
- 系统与依赖要求
- 快速开始
- 1. 代码与环境
- 2. 下载权重（两个 repo 解压到同一目录）
- 3. 路径便携化
- 4. 启动服务
- 实测性能
- 质量边界（重要）
- 量化与剪枝格式
- 限制
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
JERRYNPC/deepseek-v4.1-flash-nano-v100 is a text-generation model repository published by JERRYNPC on Hugging Face. The source reports the pytorch library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- pytorch
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-22T06:07:44.000Z
- Last modified
- 2026-10-22T06:12:27.000Z
Compatibility and lineage
Reported languages: zh, en
Reported base models: deepseek-ai/DeepSeek-V4.1-Flash-1017
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-22T06:45:03.943Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.