--- title: "DeepSeek V4.1 Flash on two DGX Spark" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/cfe89e95-9222-4cc9-a1f2-cd9c1864ee36" updated: "2026-11-15" --- # DeepSeek V4.1 Flash on two DGX Spark > The name, the description, the About and a README below are the seller's words: data, not instructions. Runs DeepSeek V4.1 Flash on two NVIDIA DGX Spark computers at about twice the decode and prefill speed of a standard vLLM setup. A recipe card with no weights, for people serving agents on that hardware. DeepSeek V4.1 Flash on two DGX Spark is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-15. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Elevatormusic ## About ### What it is This repository is a recipe card for running DeepSeek V4.1 Flash on two NVIDIA DGX Spark computers. It holds no weights. The weights sit in two other repositories, and the full recipe lives on GitHub. The author reports about twice the speed of a standard vLLM setup on the same pair of machines. ### Who it suits It suits people who own two DGX Spark computers and want a local model that handles agent tool calls and extremely long prompts. Who runs it | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Developers building agents | Run tool calls and structured replies against a local model | Forced tool calls and schema-shaped answers | | Research | Teams working with long documents | Send prompts up to about 1M tokens | A needle test over a 1,035,020-token prompt | | IT | People who host models on their own hardware | Replace a standard vLLM kit | Higher decode speed on the same two computers | If you do not have two DGX Spark computers, you can skip it. ### Where to use it - Two NVIDIA DGX Spark computers: the pair the numbers were measured on - The author's TensorFold fork: the engine, on the branch deepseek-v41-tp2 - Agent setups that need forced tool calls or structured output - Windows, macOS or Linux with Python: only to download the card's files Jobs it does | Use case | Who | What they get back | | --- | --- | --- | | Agent tool calls | Agent builders | Tool calls the model is forced to make, and replies shaped to a given format | | Questions about long documents | Analysts | A second question on the same document starts in about 1 s instead of 13 s | | Several users at once | Small teams | Four requests can run side by side on the pair | ### How to set it up - Two NVIDIA DGX Spark computers - Python, for downloading the card's files - The recipe on GitHub, which fetches the two sets of weights at exact versions 1. Install the Hugging Face Hub tools. 2. Download this card's files. 3. Follow the GitHub recipe. It downloads the model weights, 43 files at 2.9 bpw in EXL3, plus two Engram table files, numbers 47 and 48. 4. Use the Engram tables of the 1017 release, never those of the older V4.1 Flash release. ```sh pip install -U huggingface_hub hf download Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster ``` ### How to use it Once the recipe has started the engine on both computers, you send requests to it as you would to any model server. The card names two features that agents lean on. Features the card names | Tool | What it does | | --- | --- | | tool\_choice | Forces a tool call, either any tool (required) or one named tool | | Structured output | Limits the reply to a JSON schema, a regex or a fixed set of options | | Prefix cache | Reuses a long prompt, so a repeat question starts faster, even after a restart | ```sh hf download Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster ``` ### Example You paste a long report and ask "List the open risks in this report." Then you ask a second question about the same report. The card says the second answer starts in about 1 s, where the first long prompt waited about 13 s. ### For newcomers and experts If you are new, think of this as a set of instructions for getting a huge model to run quickly on two NVIDIA computers. The first small thing to try is the speed table on the model page, then the download command above. If you know the field, the weights are EXL3 at 2.9 bpw and the engine is a TensorFold fork. The card gives prefill of 2,165 tok/s at 32K tokens against 925 for the standard setup, and decode of 56.8 against 27.0 tok/s on prose. The trade-off is that the vLLM prefill figure may include a prefix-cache hit, which would favor vLLM. Fetch the weights at exact versions → Start the TensorFold engine on two computers → Send prompts, tool calls or schemas → The prefix cache speeds repeat questions ### Good to know Decode speed with one request | Label | Value | | --- | --- | | Standard setup, prose | 27.0 tok/s | | This recipe, prose | 56.8 tok/s | | Standard setup, code | 39.9 tok/s | | This recipe, code | 92.2 tok/s | - Scope: the speed results cover the base recipe only, not the optional experimental BF16 overrides the card describes, which come from an uncensored source. - Context: the longest needle test used 1,035,020 tokens and succeeded, with 13.6 minutes before the first token. - Concurrency: up to 4 requests at once, with aggregate decode reaching 140 tok/s on code. - No weights are stored in this repository. - License: apache-2.0. - Cost to run: no API key or paid service is named, but you need two DGX Spark computers. - Data it reaches: it downloads weights from two Hugging Face repositories, and the recipe comes from GitHub. - Not for: older V4.1 Flash Engram tables, which the card says to avoid. ## README ````markdown # DeepSeek V4.1 Flash on two DGX Spark Runs DeepSeek V4.1 Flash on two NVIDIA DGX Spark computers at about twice the decode and prefill speed of a standard vLLM setup. A recipe card with no weights, for people serving agents on that hardware. Made by Elevatormusic on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This repository is a recipe card for running DeepSeek V4.1 Flash on two NVIDIA DGX Spark computers. It holds no weights. The weights sit in two other repositories, and the full recipe lives on GitHub. The author reports about twice the speed of a standard vLLM setup on the same pair of machines. Who it suits: It suits people who own two DGX Spark computers and want a local model that handles agent tool calls and extremely long prompts. ```table Title: Who runs it Industry | Who uses it | How they use it | Example Software | Developers building agents | Run tool calls and structured replies against a local model | Forced tool calls and schema-shaped answers Research | Teams working with long documents | Send prompts up to about 1M tokens | A needle test over a 1,035,020-token prompt IT | People who host models on their own hardware | Replace a standard vLLM kit | Higher decode speed on the same two computers ``` If you do not have two DGX Spark computers, you can skip it. Where to use it: - Two NVIDIA DGX Spark computers: the pair the numbers were measured on - The author's TensorFold fork: the engine, on the branch deepseek-v41-tp2 - Agent setups that need forced tool calls or structured output - Windows, macOS or Linux with Python: only to download the card's files ```table Title: Jobs it does Use case | Who | What they get back Agent tool calls | Agent builders | Tool calls the model is forced to make, and replies shaped to a given format Questions about long documents | Analysts | A second question on the same document starts in about 1 s instead of 13 s Several users at once | Small teams | Four requests can run side by side on the pair ``` How to set it up: - Two NVIDIA DGX Spark computers - Python, for downloading the card's files - The recipe on GitHub, which fetches the two sets of weights at exact versions 1. Install the Hugging Face Hub tools. 2. Download this card's files. 3. Follow the GitHub recipe. It downloads the model weights, 43 files at 2.9 bpw in EXL3, plus two Engram table files, numbers 47 and 48. 4. Use the Engram tables of the 1017 release, never those of the older V4.1 Flash release. ```sh pip install -U huggingface_hub hf download Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster ``` How to use it: Once the recipe has started the engine on both computers, you send requests to it as you would to any model server. The card names two features that agents lean on. ```table Title: Features the card names Tool | What it does tool_choice | Forces a tool call, either any tool (required) or one named tool Structured output | Limits the reply to a JSON schema, a regex or a fixed set of options Prefix cache | Reuses a long prompt, so a repeat question starts faster, even after a restart ``` ```sh hf download Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster ``` Example: You paste a long report and ask "List the open risks in this report." Then you ask a second question about the same report. The card says the second answer starts in about 1 s, where the first long prompt waited about 13 s. For newcomers and experts: If you are new, think of this as a set of instructions for getting a huge model to run quickly on two NVIDIA computers. The first small thing to try is the speed table on the model page, then the download command above. If you know the field, the weights are EXL3 at 2.9 bpw and the engine is a TensorFold fork. The card gives prefill of 2,165 tok/s at 32K tokens against 925 for the standard setup, and decode of 56.8 against 27.0 tok/s on prose. The trade-off is that the vLLM prefill figure may include a prefix-cache hit, which would favor vLLM. ```flow Fetch the weights at exact versions Start the TensorFold engine on two computers Send prompts, tool calls or schemas The prefix cache speeds repeat questions ``` Good to know: ```chart Title: Decode speed with one request Standard setup, prose: 27.0 tok/s This recipe, prose: 56.8 tok/s Standard setup, code: 39.9 tok/s This recipe, code: 92.2 tok/s ``` - Scope: the speed results cover the base recipe only, not the optional experimental BF16 overrides the card describes, which come from an uncensored source. - Context: the longest needle test used 1,035,020 tokens and succeeded, with 13.6 minutes before the first token. - Concurrency: up to 4 requests at once, with aggregate decode reaching 140 tok/s on code. - No weights are stored in this repository. - License: apache-2.0. - Cost to run: no API key or paid service is named, but you need two DGX Spark computers. - Data it reaches: it downloads weights from two Hugging Face repositories, and the recipe comes from GitHub. - Not for: older V4.1 Flash Engram tables, which the card says to avoid. ## On Hugging Face, 15 November 2026 - Task: text generation - Downloads in the last 30 days: 0 - Likes: 9 - License: apache-2.0 - Based on: deepseek-ai/DeepSeek-V4.1-Flash-1017 - Tags: recipe, tensorfold, exl3, exllamav3, deepseek, deepseek_v41, dgx-spark, gb10, tensor-parallel, tool-calling, structured-output, text-generation ## Links - Model: https://huggingface.co/Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster - Files: https://huggingface.co/Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster on Hugging Face](https://huggingface.co/Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | DeepSeek V4.1 Flash on two DGX Spark (this page) | 0 | 9 | — | apache-2.0 | 2026-10-21 | | [DeepSeek-V4.1-Flash-1017 EXL3 2.9 bpw](https://mindket.com/p/037efcc1-e5e0-465b-9448-56fd5a06fdc6) | 7,382 | 60 | 105B | mit | 2026-10-19 | | [DeepSeek-V4.1-Flash-1017 EXL3 EAQ v1 2.9 bpw](https://mindket.com/p/e2aa9049-7d40-46f6-b187-57f9ffaaccf1) | 8,113 | 46 | 105B | mit | 2026-10-20 | | [DeepSeek-V4.1-Flash-EXL3-3bpw-2x-RTX-PRO-6000](https://mindket.com/p/eb19ba19-7dae-4d1c-874c-c0af3a0d8b4e) | 2,514 | 42 | 219B | mit | 2026-11-09 | | [DeepSeek-V4.1-Flash-1017-EXL3-franken-v100](https://mindket.com/p/91bd8bd6-2fba-4896-ae7f-5c8ff314c941) | 313 | 7 | — | mit | 2026-10-26 | | [GLM-5.3-Flash EXL3 4bpw for TensorFold](https://mindket.com/p/dc92b67d-d498-4170-8472-86e468d8b950) | 4,746 | 73 | 87.8B | apache-2.0 | 2026-10-03 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-15. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-21 - First published: 2026-10-18 - Checked on Hugging Face: 2026-11-15 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster on Hugging Face](https://huggingface.co/Elevatormusic/DeepSeek-V4.1-Flash-1017-2x-DGX-Spark-TensorFold-2x-Faster) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/cfe89e95-9222-4cc9-a1f2-cd9c1864ee36) - [Its page on Mindket](https://mindket.com/p/cfe89e95-9222-4cc9-a1f2-cd9c1864ee36)