DeepSeek-V4.1-Flash-1017-EXL3-TensorFold-2x-DGX-Spark
DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw on 2x NVIDIA DGX Spark (GB10) with TensorFold: 2.1-2.3x the vLLM kit's decode speed.
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Visit website ↗ Source listing ↗
GITHUB · launched Oct 18, 2026 · 52 upvotes (top 27%)
- Horizontal
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
- deepseek
- dgx-spark
- exl3
- gb10
- llm-inference
- nvidia
- +2 more
Similar launches
See all 314 similar launches →Could you build this?
No This is an inference engine optimization for a large quantized model across two DGX Spark machines, with custom tensor-parallel kernels and quantization work. It needs GPU systems expertise and specialized hardware.
Competitors
Other products that read as similar to this one : 314 launches clear the similarity bar, closest 8 shown.
Attention rank: #100 of 315 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 348 days after the earliest competitor.
- deepseek-v41-tensorfold-spark · github · 2026-10-03 · 16 upvotes · similarity 0.89
- DeepSeek-V4.1-Flash-EXL3-TensorFold-2x-DGX-Spark · github · 2026-10-04 · 12 upvotes · similarity 0.89
- DeepSeek-v4.1-Flash-1017-2x-DGX-Sparks · github · 2026-10-18 · 218 upvotes · similarity 0.87
- DeepSeek-V4.1-Flash-EXL3-vLLM-2x-DGX-Spark · github · 2026-09-10 · 20 upvotes · similarity 0.82
- dgx-spark-deepseek-v41 · github · 2026-10-12 · 32 upvotes · similarity 0.79
- deepseek-v4.1-tensorfold-tp2-2xgb10 · github · 2026-10-04 · 20 upvotes · similarity 0.76
- DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks · github · 2026-09-13 · 206 upvotes · similarity 0.75
- DeepSeek-V4.1-Flash-vLLM-DGX-Spark · github · 2026-09-10 · 65 upvotes · similarity 0.75
Other launches for this product
- No other launches for this product.