--- license: mit base_model: - deepseek-ai/DeepSeek-V4.1-Flash-1017 pipeline_tag: text-generation tags: - slipstream - dgx-spark - exl3 - mxfp8 - deepseek --- # DeepSeek-V4.1-Flash-Slipstream DeepSeek-V4.1-Flash (1017) for the Slipstream inference engine: our own EXL3 quantization of the routed experts with K2/K3/K4 bit widths per expert (3.04 bpw, chosen from routing statistics and calibrated on 1017), dense weights in MXFP8 (lossless from FP8), the checkpoint's DSpark block drafter, the Engram tables and the vision tower. These are **Slipstream weight files** (`weights.vbin` + `index.json` per directory), the engine's own pre-packed format. They run only with Slipstream; they are not safetensors and do not load in other runtimes. Built with Slipstream's converters at commit `20c2dd9` (2026-10-31). Base model: [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017). Engine: [Slipstream](https://github.com/Interactify/slipstream) (engine code release coming soon). Hardware: two NVIDIA DGX Spark (GB10, 128 GB each) connected over their 200 GbE link. ## Contents | Directory | What | Node | |---|---|---| | `dense1017_r0` | dense weights + Engram rows, rank 0 | first | | `dense1017_r1` | dense weights + Engram rows, rank 1 | second | | `x3_1017_r0` | EXL3 routed experts, rank 0 | first | | `x3_1017_r1` | EXL3 routed experts, rank 1 | second | | `dsp_1017_r0 / _r1` | DSpark drafter | first / second | | `head4_1017_r0 / _r1` | 4-bit output head for drafting | first / second | | `dx3_1017_r0 / _r1` | 4-bit dense copies for the `fast` profile | first / second | | `vision1017` | vision tower | first | | `orig` | tokenizer, config and chat template | first | ## Download On the first Spark (rank 0, runs the HTTP server): ```bash hf download Interactify/DeepSeek-V4.1-Flash-Slipstream --local-dir ~/dsv41 \ --include "*_r0/*" "vision1017/*" "orig/*" ``` On the second Spark (rank 1): ```bash hf download Interactify/DeepSeek-V4.1-Flash-Slipstream --local-dir ~/dsv41 --include "*_r1/*" ``` The tokenizer, config and chat template are included (`orig/`); nothing else needs downloading. The directory names match the defaults in Slipstream's `server/models.json`, so no configuration is needed. ## Run ```bash python server/slipstream.py serve deepseek-v4.1-flash --profile balanced ``` The server speaks the OpenAI and Anthropic APIs on port 8080. See the Slipstream README for profiles, the router and engine settings. ## Measured on Slipstream - Decode, one stream (fast profile): structured 126 / prose 62 / code 97 / JSON 105 tokens/s; four streams in total 136 / 101 / 131 / 157. - Prefill 8K-32K: about 2,300 tokens/s (exact). - Quality against a CPU reference with the original MXFP4 experts (5 texts of 1024 tokens): KL 0.007-0.041, top-1 90-98 %, perplexity within 0.5 %. - Greedy output with DSpark drafts is identical to decoding without drafts. ## Notes - Context up to 524,288 tokens. - Needs both Sparks (no single-Spark variant). ## License MIT, as the base model (DeepSeek). See `LICENSE` and `NOTICE`.