Skip to content

NewsRAM

Edge0-145B Claims a 145B AI Model Can Run on One 24GB GPU: What PC Would You Need?

Edge0 has released open weights for Edge0-145B, a mixture-of-experts model with about 10 billion active parameters. Edge0 says it runs on one 24GB NVIDIA GPU by keeping roughly 31-38GB of the model in system RAM. All performance figures are Edge0's own.

By , Hardware News & Market Editor

3 min read

Edge0-145B Claims a 145B AI Model Can Run on One 24GB GPU: What PC Would You Need?

Edge0 released Edge0-145B and a smaller Edge0-120B on 12 November 2026, with open weights and its own inference software. The headline claim is that a 145-billion-parameter model, a size usually associated with servers, can run on a single consumer GPU or an Apple Silicon laptop.

The memory, speed and benchmark figures below are Edge0's own, from its launch blog and its GitHub model documentation, read on 14 November 2026. We have not seen independent verification of them yet, so treat every number here as a vendor claim.

How a 145B model fits on a gaming GPU

Edge0-145B is a mixture-of-experts model. It has 145B parameters in total, but Edge0 says only about 10.12B are active for each token. The rest are "experts" that are only needed some of the time. Edge0's documentation says the models are derived from Qwen3.8-Flash-Next and run on edge0-strata, the company's fork of the Strata inference engine, rather than on a mainstream app such as Ollama or LM Studio.

The trick is spreading the model across three kinds of memory:

  • GPU memory holds the most frequently used "hot" experts.

  • System RAM holds a larger expert library, which the blog puts at about 40GB.

  • The SSD holds a large vocabulary table (about 48GB, according to the blog), which is read on demand.

Edge0's GitHub page gives a concrete example on a 24GB card. The Q3_K build has 40.81 GiB of weights, held as about 23.14 GiB in VRAM plus 31.28 GiB in system RAM. The NVFP4 build (47.79 GiB) uses about 23.25 GiB of VRAM plus 38.27 GiB of RAM. The blog separately quotes a 29GB peak memory figure for its laptop comparison.

Edge0's own speed figures

These are the company's numbers, not ours:

Edge0's test machine (Q3_K build)

Chat decode, tokens/s (Edge0's figure)

RTX 5090 D 24GB

99.7

RTX 4090 24GB

69.9

The same 5090 D limited to 16GiB VRAM and 20GiB RAM

36.8

Apple M2 Ultra

60.9

Edge0 also publishes benchmark scores, including 86.5 on Terminal-Bench 2.1 and 64.6 on DeepSWE 1.1, and says these are competitive with some cloud models. Its blog says those comparisons come from its own internal evaluations. We are reporting them, not endorsing them.

What PC would you need?

Reading Edge0's own figures, a sensible Windows target looks like this:

  • GPU: an NVIDIA card with 24GB of VRAM, such as the RTX 4090 or RTX 5090 class it lists. Edge0 says day-one support covers NVIDIA platforms, including the RTX 4090 and 5090, plus Apple M-series chips. We did not see AMD Radeon in its supported list.

  • System RAM: 64GB. The Q3_K example uses about 31GB of RAM on top of the GPU, and Windows and your other apps need room too. A 32GB PC would be very tight. Our guide to how much RAM you need for local AI explains why system RAM matters once a model spills out of VRAM.

  • Storage: a fast NVMe SSD with plenty of free space, because part of the model is streamed from disk.

A 16GB card is not ruled out. Edge0's constrained 16GiB VRAM and 20GiB RAM test still produced output, but at a much lower figure. If you are buying a GPU for local AI, our best GPU for local LLMs guide explains why VRAM is still the first thing to check.

Why caution is sensible

  • Quantisation matters. The Q3_K build is a heavily compressed version. Our GGUF and quantisation explainer covers what that trade-off means for quality.

  • Different software. Edge0's speeds depend on its own scheduler, so do not expect the same results by loading another large model in a general-purpose app.

  • Vendor benchmarks. Wait for independent tests before deciding the model is as capable as Edge0 says. We took the same approach with Ripple-65B Preview in Ollama.

Our verdict

Edge0-145B is a genuinely interesting experiment: a very large open model designed from the start to be split across VRAM, system RAM and an SSD. If Edge0's figures hold up, a 24GB NVIDIA card with 64GB of RAM is the realistic Windows setup, and 32GB of RAM is the bottleneck to fix first. Do not buy hardware for it until independent testing appears.

The bottom line

Edge0-145B is a genuinely interesting experiment: a very large open model designed from the start to be split across VRAM, system RAM and an SSD. If Edge0's figures hold up, a 24GB NVIDIA card with 64GB of RAM is the realistic Windows setup, and 32GB of RAM is the bottleneck to fix first. Do not buy hardware for it until independent testing appears.

Sources

  1. 01Edge0, Introducing Edge0-145B: Frontier AI Capabilities on Your Own Computer (12 November 2026)
  2. 02Edge0, Edge0 145B and Edge0 120B model documentation (GitHub)

About the author

Eleanor Shaw

Hardware News & Market Editor

Eleanor covers daily PC hardware news, silicon roadmaps, driver releases and UK retail pricing trends across AMD, Intel and Nvidia. She tracks board-partner specifications, industry standards bodies (PCI-SIG, JEDEC, VESA) and supply-chain shifts affecting British PC builders.

More from Eleanor Shaw

Read next

Patriot Launches AI Matrix SSDs and DDR5 Kits Pitched at Local AI PCs

News

Patriot Launches AI Matrix SSDs and DDR5 Kits Pitched at Local AI PCs

Patriot's AI Matrix range pairs MS560 (Gen5), MS450 (Gen4) and MS350 (Gen3) M.2 SSDs with DDR5 kits in PRO, Mid and Entry tiers matched to local LLM sizes. The SSDs carry a two-year warranty, DRAM specs aren't fully published and there's no UK price yet.

Eleanor Shaw3 min

Best 128GB DDR5 RAM Kit in 2026: Five 2x64GB Kits Compared

Best Picks

Best 128GB DDR5 RAM Kit in 2026: Five 2x64GB Kits Compared

Five 2x64GB DDR5 kits compared on their makers' specs: the G.SKILL Flare X5 DDR5-6000 CL34 is our pick for Ryzen, with the Trident Z5 Neo RGB for lighting, the Ripjaws S5 DDR5-6400 for Intel and the Crucial Pro DDR5-5600 if you'd rather not overclock.

Hannah Vance4 min