Model overview
DeepSeek-V4.1-Flash-1017 (552B MoE + 196B Engram) quantized to **187.6 GB**, intended for two RTX 3090s and 192 GB of RAM with exact routing. Runs on **dsx**, a Rust + CUDA engine made for this model. This is a V4.1 GSQ GGUF for dsx, not a llama.cpp / Ollama / LM Studio GGUF. Measured with `dsx eval` on Lucebox's 1017 eval set: 8 × 1024 held-out tokens, KL and top-1 against the FP8/FP4 teacher's top-256 log-probs. All experts were resident (`0 left in the file`). Measured on this machine with the new `dsx` engine: 2× RTX 3090, 192 GB RAM, NVMe SSD, `--ctx 262144`, all experts resident.
Key features
特点摘要待依据来源补齐，不凭模型名称推断能力。
Limitations & considerations
Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.
Source prices & cost analysis
Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.
| Source / channel | Input | Output | Billing unit | Collected at |
|---|---|---|---|---|
| No verified prices yet. Check the source channel. | ||||
Estimate monthly base token costs
Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.
Public benchmarks & run configuration
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。
View full indexed rankings →Frequently asked questions
Do open weights permit free commercial use?
Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.
Are these real-time billing prices?
These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.
Sources & traceability
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。