DeepSeek V4.1 Flash official weights on 4x DGX Spark: 66 tok/s single stream, 173 tok/s at 16 concurrent
TensorFold runs the full official weights on a switchless 4x DGX Spark TP4 setup with 1M context and 16 concurrent sessions, reporting per-concurrency decode speeds and 4000+ tok/s prefill.
Run DeepSeek V4.1 Flash 1017 with the full official weights on your 4x DGX Sparks, using TensorFold, Abliterated! 🔥 - Full support for switchless TP4 - 1M context, 16M total KV cache - 16 concurrent sessions with 1M each - 15 GB of free mem per Spark after load - OFFICIAL weights, no further quantization! - Needle passed at 100% depth - ABLIT is off by default. Gated. Performance tested on a switchless TP4. It should be faster with a switch. Decode speeds, non-greedy, thinking on: - 66 tok/s on prose, single stream - 96 tok/s on prose, 2 concurrent streams - 173 tok/s on prose, 16 concurrent streams Decode speeds, greedy, thinking off: - 85 tok/s on prose, single stream - 113 tok/s on prose, 2 concurrent streams - 210 tok/s on prose, 16 concurrent streams Decode speeds per stream in deep context (128k), non-greedy, thinking on: - 58.6 tok/s on prose, single stream - 83 tok/s on prose, 2 concurrent streams - 132 tok/s on prose, 8 concurrent streams Prefill: 4000+ tok/s up to 256k. This is the best model to run if you have 4x DGX Sparks, bar none! It works so well on the Sparks that it's unbelievable. Get it here: https://mia-ai.net/models/DeepSeek-V4.1-Flash-1017-4x-DGX-Sparks-TensorFold