Nvidia launched RTX Spark laptops on Friday with up to 128GB of shared memory and a 74-billion-parameter model it says fits in 24GB. A local agent pilot is now possible on Windows, though every figure so far comes from Nvidia.
Reality
- Evidence35
- Adoption
- Not scored
- Hype gap+30
- Incentives70
- Confidence60
buildOne report1 publisher Unsloth's figures suggest a 128 GB Mac can run NVIDIA's Nemotron 3.5 Super VL with vision
Nemotron 3.5 Super VL, NVIDIA's 120B model, had GGUF, MLX, FP8 and EXL3 conversions on Hugging Face a day after its October 15 release. The roughly 128 GB memory figure comes from a DEV Community write-up whose author did not run the model.
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap+15
- Incentives
- Not scored
- Confidence55
buildOne report1 publisher The Neuron clocks NVIDIA's 74B Nemotron Bolt at 65.5 tokens per second on a laptop
The Neuron measured NVIDIA's Nemotron 3.5 Bolt 74B-A9B at 65.5 tokens per second on a laptop in a hands-on test. The build was heavily compressed, and the review's tool-assisted wins went to the hosted Super VL.
Reality
- Evidence45
- Adoption
- Not scored
- Hype gap+15
- Incentives
- Not scored
- Confidence50
buildOne report1 publisher Surface Laptop Ultra edges an M4 Max Mac Studio on local models, plugged in
Microsoft's $4,300 Surface Laptop Ultra ran local models generally a bit faster than an M4 Max Mac Studio, The New Stack's reviewer found. The edge was measured on the charger with models sized to the machine, so buyers should check their own model mix.
Reality
- Evidence50
- Adoption
- Not scored
- Hype gap+15
- Incentives
- Not scored
- Confidence55
buildConfirmed12 publishers NVIDIA says its Nemotron 3.5 Bolt 74B-A9B agent model fits in 24GB and will ship with open weights, data and recipes. The footprint, the license terms and the quality claims stay unverified until the weights are live and outside testers have run them.
Perspective Coverage
12 publishers
- Builder
- Builder 40%
- Operator
- Operator 35%
- Investor
- Investor 25%
Reality
- Evidence42
- Adoption
- Not scored
- Hype gap+25
- Incentives60
- Confidence58
buildConfirmed2 publishers Meta's Muse Spark Open, an 816B-parameter coding model, is now on SageMaker JumpStart in BF16 and 4-bit NVFP4 variants. The NVFP4 build needs roughly a quarter of the memory, and memory capacity decides which instance you rent.
Reality
- Evidence35
- Adoption
- Not scored
- Hype gap+15
- Incentives
- Not scored
- Confidence70
buildConfirmed3 publishers Black Forest Labs' open FLUX.3 Image Klein weights now load in Hugging Face Diffusers for self-hosted image generation and editing. Hugging Face times the distilled checkpoint at about 2 seconds per 1024 x 1024 image on an H100, and The Decoder reports an INT8 build for 8 GB cards.
Perspective Coverage
3 publishers
- Builder
- Builder 52%
- Operator
- Operator 23%
- Investor
- Investor 25%
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap+20
- Incentives60
- Confidence68
buildOne report1 publisher ExecuTorch lowers PyTorch models straight to CMSIS-NN kernels on Cortex-M microcontrollers
PyTorch's ExecuTorch Cortex-M backend ran four MLPerf Tiny models at 21.5 ms or less each, using under 90 KiB of RAM on a single Cortex-M55 core. The test is the PyTorch team's own, on one Alif Ensemble E8 board, so the figures hold for similar cores and INT8 models.
Reality
- Evidence45
- Adoption
- Not scored
- Hype gap+15
- Incentives55
- Confidence50
buildOne report1 publisher A clean config diff against Qwen3.8-27B does not let AREX-2 reuse the base model's serve command
BAAI's AREX-2 config declares one multi-token-prediction layer, but its weight index lists 0 such tensors against Qwen3.8-27B's 15. Its dev.to testers say the base-model drafter and quant need rechecking too, though they have not run AREX-2.
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap−10
- Incentives
- Not scored
- Confidence50
buildOne report1 publisher One 80 GB GPU holds 4-bit 70B weights and at most 11 conversations of 8,192 tokens
Serving a 70B model takes about 141 GB of GPU memory for weights at 16-bit, 73 GB at FP8 and 40 GB at 4-bit, according to a dev.to post. Fine-tuning takes about 50 GB with QLoRA and 1.1 TB with full AdamW. The post maps both onto GPU setups and hourly rental prices.
Reality
- Evidence72
- Adoption
- Not scored
- Hype gap+5
- Incentives
- Not scored
- Confidence68
buildOne report1 publisher NVIDIA and Princeton cache SSM inputs in place of state to speed hybrid-model decoding
NVIDIA and Princeton's Dao AI Lab cache SSM inputs instead of state, targeting a decode step where SSM layers are the largest component up to 100K tokens. ReplaySSM is already integrated into TensorRT-LLM, vLLM and FlashInfer, NVIDIA says.
Reality
- Evidence45
- Adoption
- Not scored
- Hype gap
- Not scored
- Incentives55
- Confidence50
buildOne report1 publisher SoloQ's 45% FLOP cut for diffusion LLMs rests on one dev.to post and an unnamed lead author
SoloQ, a calibration-free quantizer for diffusion LLMs, cuts inference FLOPs about 45%, according to a dev.to post on an arXiv paper dated 2026-10-05. That write-up is the only source, and its cost numbers come from a scenario with an unnamed provider.
Reality
- Evidence22
- Adoption
- Not scored
- Hype gap+45
- Incentives
- Not scored
- Confidence60
Tencent open-sources a 33-language translation model that fits on a device in 440 MB
Tencent has open-sourced its Hy-MT2 translation models for 33 languages, with the smallest compressed to 440 MB to run on devices. The claim that the small model beats Microsoft's API is Tencent's own, so teams paying per call have a candidate to test.
Reality
- Evidence30
- Adoption
- Not scored
- Hype gap+35
- Incentives70
- Confidence40
buildConfirmed2 publishers Microsoft plans to run MAI Code 1.1 Flash on developers' machines in GitHub Copilot, with a limited rollout starting by end-October 2026. Its figures come from one high-end laptop and local pricing is undisclosed, so teams cannot yet size the hardware or the bill.
Reality
- Evidence55
- Adoption12
- Hype gap+20
- Incentives55
- Confidence58
buildOne report1 publisher VIDRAFT ships a 111GB Darwin-180B that pages its experts from SSD on 8GB-VRAM laptops
VIDRAFT released a 111GB, 4-bit build of its 180B-parameter Darwin model that it says runs on a laptop with 8GB of VRAM and 32GB of RAM. Air-gapped teams still need a measured token rate on that laptop before they can price it against a server.
Reality
- Evidence30
- Adoption
- Not scored
- Hype gap+40
- Incentives85
- Confidence40
buildOne report1 publisher Strata Hits 110.8 tok/s on an RTX 4090 by Activating Only 6B Parameters per Token
Strata runs a 125B-class Qwen model at about 100 tok/s on one RTX 4090 because its sparse MoE activates only about 6B parameters per token. The design moves the hardware bill to system RAM, and the 100 tok/s figure holds mainly for code and structured output.
Reality
- Evidence45
- Adoption15
- Hype gap+40
- Incentives
- Not scored
- Confidence40
buildOne report1 publisher NVIDIA's RTX Spark PCs fit a 4-bit 70B model in 128GB with about 90GB to spare
NVIDIA's RTX Spark PCs from Lenovo and Acer ship in October with up to 128GB of shared CPU/GPU memory, enough for a 4-bit 70B model. Long-context agents now fit on owned hardware, though a cost comparison with cloud inference waits on system prices.
Reality
- Evidence30
- Adoption
- Not scored
- Hype gap+35
- Incentives
- Not scored
- Confidence30
buildConfirmed2 publishers Salvatore Sanfilippo's open-source ds4 engine runs a short list of large open-weight models locally by compressing their routed experts to about two bits. Even compressed, the supported builds need high-memory Macs or GPU systems that most people do not already own.
Reality
- Evidence55
- Adoption30
- Hype gap+20
- Incentives
- Not scored
- Confidence60
buildOne report1 publisher VIDRAFT's 4-bit Darwin-180B build streams most of its weights from SSD on a 40 GB laptop
VIDRAFT says POCKET-Darwin-180B, a 111 GB 4-bit GGUF build of its 180B mixture-of-experts model, runs in llama.cpp on about $1,400 of consumer hardware. The accuracy evidence so far is one MMLU-Pro comparison that VIDRAFT reports itself.
Reality
- Evidence30
- Adoption
- Not scored
- Hype gap+45
- Incentives60
- Confidence35
buildOne report1 publisher Helion's autotuned GEMM outruns vLLM's CUTLASS and DeepGEMM paths on Hopper GPUs
Helion's autotuned GEMM beat vLLM's default CUTLASS and DeepGEMM backends on Hopper GPUs, by more than 10% throughput on some workloads, its authors report. The gain rests on per-shape tuning that can run for hours, a cost teams pay in place of kernel maintenance.
Reality
- Evidence35
- Adoption15
- Hype gap+10
- Incentives70
- Confidence40