---
type: "Article"
title: "DeepSeek-V4.1-Flash EXL3 2.77 bpw with vLLM on 2× DGX Spark"
description: "DeepSeek-V4.1-Flash EXL3 2.77 bpw with vLLM on 2× DGX Spark: recipe by 0xSero with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/0xsero--dsv41-flash-exl3-2.77bpw-vllm-2x-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-24T16:15:37.543Z"
status: "stable"
---

# DeepSeek-V4.1-Flash EXL3 2.77 bpw with vLLM on 2× DGX Spark

DeepSeek-V4.1-Flash EXL3 2.77 bpw with vLLM on 2× DGX Spark: ~29 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [0xSero](https://www.contextstudios.ai/local-ai/creators/0xsero.md)
- Engine: vLLM-Fork (EXL3-MoE + B12X-Kernel) ghcr.io/0xsero/deepseek-v4.1-flash-spark@sha256:5668e35e
- Quantization: EXL3 MUL1 2.77 bpw routed experts (K2/K3/K5-Mix), Rest upstream unverändert; FP8 KV
- Model family: DeepSeek-V4.1-Flash
- Hardware: dgx-spark x2
- Context: 262144
- Artificial Analysis Intelligence Index: 39.5 ([source](https://artificialanalysis.ai/models/deepseek-v4-1-flash))

## All numbers

- ~29 tok/s (Everyday; Everyday, 1 request, prose prompt, with DSpark (7 draft tokens) (per recipe)) — [source](https://github.com/0xSero/DeepSeek-V4.1-Flash-Two-Sparks#measured)
- decode_tps: 29 (1 request) — [source](https://github.com/0xSero/DeepSeek-V4.1-Flash-Two-Sparks#measured)
- decode_tps: 60 (2 parallel requests) — [source](https://github.com/0xSero/DeepSeek-V4.1-Flash-Two-Sparks#measured)
- prefill_tps: 2061 (1 request) — [source](https://github.com/0xSero/DeepSeek-V4.1-Flash-Two-Sparks#measured)

## Weights

- [0xSero/DeepSeek-V4.1-Flash-Spark](https://huggingface.co/0xSero/DeepSeek-V4.1-Flash-Spark) (main, mit)
- [deepseek-ai/DeepSeek-V4.1-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash) (base, mit)

[https://github.com/0xSero/DeepSeek-V4.1-Flash-Two-Sparks](https://github.com/0xSero/DeepSeek-V4.1-Flash-Two-Sparks)

## Related

- [Local AI on your hardware.](https://www.contextstudios.ai/local-ai.md)