English translation is being prepared.
Matched fieldsTitle
←Search results
Search “NVIDIA”
English translation is being prepared.
Matched fieldsTitle
Artificial Analysis publishes AA-AgentPerf results for Muse Spark Open
Artificial Analysis on October 24, 2026 published on AA-AgentPerf preliminary test results for Meta's newly open-weight model Muse Spark Open. The model is a 816B-parameter, 42B-active MoE, scoring 39 on the Artificial Analysis Intelligence Index. Tests show that NVIDIA B300 and GB300 each reach about 150M tokens/s per megawatt of power under throughput-first configurations; GB300 reaches about 108M and B300 about 92M at 100 tok/s output speed; AMD MI355X reaches 70M tokens/s per megawatt at 65 tok/s. Of the model's 62 layers, 46 use 2,048-token sliding window attention, reducing KV cache requirements at 1M context by about 75% versus full attention. Meta released an NVFP4 checkpoint, and AMD released an MXFP4 checkpoint. There are currently no subsequent development facts.
esults for Meta's newly open-weight model Muse Spark Open. The model is a 816B-parameter, 42B-active MoE, scoring 39 on the Artificial Analysis Intelligence Index. Tests show that NVIDIA B300 and GB300 each reach about 150M tokens/s per megawatt of power under throughput-first configurations; GB300 reaches about 108M and B300 about 92M at 100 tok/s output speed; AMD MI355X reaches 70M tokens/s per megawatt at 65 tok/s. Of the model's 62 layers, 46 use 2,048-token sliding window attention, reduci
Matched fieldsSummary
Shopify shares how Sidekick uses a post-trained open-source model as the GraphQL sub-agent
On October 21, 2026, the Shopify engineering team, in a talk at NVIDIA GTC Berlin 2026, shared the model division-of-labor plan for its e-commerce assistant Sidekick: a frontier model handles conversation planning, while a self-deployed open-source model handles the GraphQL sub-agent. The team chose the MoE model Nemotron 3.5 Lightning, with 30 billion total parameters and 3 billion parameters activated per token; after 6 rounds of post-training and 61,000 repair samples, the review score rose from 37.7 out of the box to 74.5, slightly above the frontier model's 73. On GraphQL tasks, the median response was 0.87 seconds, versus 6.50 seconds for the frontier model API, at roughly 90% lower cost. Currently this talk is a single-source report, with no follow-up developments yet.
On October 21, 2026, the Shopify engineering team, in a talk at NVIDIA GTC Berlin 2026, shared the model division-of-labor plan for its e-commerce assistant Sidekick: a frontier model handles conversation planning, while a self-deployed open-source model handles the GraphQL sub-agent. The team chose the MoE model Nemotron 3.5 Lightning, with 30 billion total parameters and 3 billion parameters activated per token; after 6 rounds of post-training and 61,000 repair samples, the review score rose f
Matched fieldsSummary
n8n blog introduces running AI workflows locally on DGX Spark
On October 19, 2026, the n8n blog published a tutorial on how to deploy a complete model stack locally on a single NVIDIA DGX Spark, enabling n8n workflows to handle transcription, OCR, document Q&A, and image generation without calling cloud APIs. The tutorial states that the entire stack exposes an OpenAI-compatible endpoint through LiteLLM, with the main model being the NVFP4 version of Qwen3.6-35B-A3B, achieving a generation speed of 120 tokens/s for a single user and 359 tokens/s combined for eight users. The author's hands-on testing found that image generation reduces conversation speed to about one-third, and recommends that small teams queue image tasks or schedule them outside working hours. Currently, this content has only the n8n blog as its source.
On October 19, 2026, the n8n blog published a tutorial on how to deploy a complete model stack locally on a single NVIDIA DGX Spark, enabling n8n workflows to handle transcription, OCR, document Q&A, and image generation without calling cloud APIs. The tutorial states that the entire stack exposes an OpenAI-compatible endpoint through LiteLLM, with the main model being the NVFP4 version of Qwen3.6-35B-A3B, achieving a generation speed of 120 tokens/s for a single user and 359 tokens/s combined f
Matched fieldsSummary
heise online publishes benchmark test of RTX Spark laptop chip
On October 16, 2026, heise online published a hands-on test of Nvidia's first laptop chip, the N1X (brand name RTX Spark). The tested model was the Asus ProArt P14, which supports up to 128 GB of unified memory; the test unit was configured with 32 GB of memory plus a 1 TB SSD and priced at 3,300 euros. When testing Qwen 3.8-27B with llama-bench, the generation speed was about 14.5 tokens/s, slightly faster than the Apple M6 and Strix Halo but slower than the M5 Pro; switching to the MoE model Qwen 3.6-35B-A3B reached nearly 61 tokens/s. Prompt processing speed was better than that of Strix Halo and the M5 Pro and M6, but fan noise at full load reached a maximum of 2.7 sone, and the fans also spin up when idle. The author also tried installing Ubuntu; after filling in the drivers themselves, both models ran 14% and 9% faster under Linux than under Windows.
On October 16, 2026, heise online published a hands-on test of Nvidia's first laptop chip, the N1X (brand name RTX Spark). The tested model was the Asus ProArt P14, which supports up to 128 GB of unified memory; the test unit was configured with 32 GB of memory plus a 1 TB SSD and priced at 3,300 euros. When testing Qwen 3.8-27B with llama-bench, the generation speed was about 14.5 tokens/s, slightly faster than the Apple M6 and Strix Halo but slower than the M5 Pro; switching to the MoE model Q
Matched fieldsSummary
n8n blog introduces running AI workflows locally on DGX Spark
On October 19, 2026, the n8n blog published a tutorial on how to deploy a complete model stack locally on a single NVIDIA DGX Spark, enabling n8n workflows to handle transcription, OCR, document Q&A, and image generation without calling cloud APIs. The tutorial states that the entire stack exposes an OpenAI-compatible endpoint through LiteLLM, with the main model being the NVFP4 version of Qwen3.6-35B-A3B, achieving a generation speed of 120 tokens/s for a single user and 359 tokens/s combined for eight users. The author's hands-on testing found that image generation reduces conversation speed to about one-third, and recommends that small teams queue image tasks or schedule them outside working hours. Currently, this content has only the n8n blog as its source.
Matched fieldsSummary
View story:n8n blog introduces running AI workflows locally on DGX Spark
Artificial Analysis launches HealthBench and HealthBench…
Artificial Analysis has launched leaderboards for OpenAI's two health dialogue benchmarks, HealthBench and HealthBench Professional; the former contains 5,000 conversations with general users and health workers, while the latter consists of 525 conversations all aimed at clinicians. On HealthBench Professional, GPT-6 Astra (max) ranks first with a length-adjusted score of 66.0%, GPT-6.1 Sol (max) is at 65.1%, and Claude Sonnet 5.5 (max with fallback) is at 63.0%. On HealthBench, Claude Sonnet 5.5 (max with fallback) leads at 62.1%, while DeepSeek V4.1 Flash (max) is at 60.9%; Claude Opus 5.5 and Claude Fable 5.1 average about 5,900 characters per answer and lose more than 11 points after length adjustment.
Artificial Analysis has launched leaderboards for OpenAI's two health dialogue benchmarks, HealthBench and HealthBench Professional; the former contains 5,000 conversations with general users and health workers, while the latter consists of 525 conversations all aimed at clinicians. On HealthBench Professional, GPT-6 Astra (max) ranks first with a length-adjusted score of 66.0%, GPT-6.1 Sol (max) is at 65.1%, and Claude Sonnet 5.5 (max with fallback) is at 63.0%. On HealthBench, Claude Sonnet 5.
Matched fieldsBody
English translation is being prepared.
Matched fieldsSummary
Aleph Alpha Releases Kolibri-1: A 78B-Parameter Open-Weight Model for German-Language Reasoning
Aleph Alpha has released the open-weight model Kolibri-1, with 78B total parameters. It uses a MoE architecture with 384 experts and 6 routed experts, activating only 3.46B parameters during inference, with a 256K Token context that can be extrapolated to about 1 million Tokens. The model focuses on German and English, and its tokenizer segments German words more token-efficiently; for example, the German Bundestag glossary requires only 1137 Tokens, whereas the compared DeepSeek-V4.1-Flash requires 1910 Tokens. Pretraining used 20 trillion Tokens, with data current as of June 18, 2026. The author's hands-on test found its answers correct and its German-language reasoning process evident, and stated that the Merlin-Arthur protocol makes the model hallucinate less in benchmarks, but its actual performance still needs to be verified in real-world use.
Aleph Alpha has released the open-weight model Kolibri-1, with 78B total parameters. It uses a MoE architecture with 384 experts and 6 routed experts, activating only 3.46B parameters during inference, with a 256K Token context that can be extrapolated to about 1 million Tokens. The model focuses on German and English, and its tokenizer segments German words more token-efficiently; for example, the German Bundestag glossary requires only 1137 Tokens, whereas the compared DeepSeek-V4.1-Flash requ
Matched fieldsBody
English translation is being prepared.
Matched fieldsSummary
English translation is being prepared.
Matched fieldsSummary
Baseten Optimizes Qwen3-ASR Batch Transcription, Boosting Single-GPU Throughput by 7x
The Baseten engineering team, through native audio decoding, KV cache FP8 quantization, and reduced host-device synchronization, increased batch transcription throughput for Qwen3-ASR 1.7B on a single RTX PRO 6000 by 7x and reduced latency by 6.9x. After optimization, the transcription cost for one hour of audio is approximately $0.0013, i.e., 1/10 of a cent per audio hour, with no significant change in word error rate. The optimized version has been made the default deployment in the Baseten Model Library and can be called through an OpenAI-compatible transcription client.
The Baseten engineering team, through native audio decoding, KV cache FP8 quantization, and reduced host-device synchronization, increased batch transcription throughput for Qwen3-ASR 1.7B on a single RTX PRO 6000 by 7x and reduced latency by 6.9x. After optimization, the transcription cost for one hour of audio is approximately $0.0013, i.e., 1/10 of a cent per audio hour, with no significant change in word error rate. The optimized version has been made the default deployment in the Baseten Mo
Matched fieldsBody
English translation is being prepared.
Matched fieldsBody
English translation is being prepared.
Matched fieldsBody
English translation is being prepared.
Matched fieldsBody