I only use the models available on the cheap plan. I like that the first thing it does is an internet search so it doesn’t say anything too stupid. I’d say it’s as good as any ai product 🤷

Thank you so so much for pointing out ROCmFP4. I have been tinkering with my RDNA 3 framework on llama. I was struggling with ROCm llama.cpp and have been using vulcan in the meantime. I know there’s some issues on the llama.cpp github to try and fix my issue (UMA stuff), but haven’t come across this specific project. Gonna try it out

Do you have a walk through for setup?

I’m on the strix halo 128 gb variant and while I got ollama working fine, i haven’t gotten any of these multi headed setups working

Openrouter is also nice for this. You can use real cheap models for embedding and the bigger ones for the actual research.

AMD Strix is an APU, optimized for AI. It is the cheapest option I am aware of to run bigger models at home. 2k for 56GB VRAM, and less den 300W total power Budget.

One could run smaller models. But for the context sizes required for research work, that is nearly impossible.

Also, external services, like openrouter, can be used to use models hosted in the cloud.

But for self hosted, you need something that can run models with at least 15GB of VRAM + Context. For comparison. Our highly quantized model uses 20GB of vram. For our 4 slots we need another 20GB on top of it (around 5GB for 254k tokens), making it 40GB.

What my Qwen 3.6 35B setup spat out to this prompt. Used 20-something sources:

Based on my research, here’s a comprehensive overview of the current state of nuclear fusion research:

Current Major Breakthroughs

The field has seen remarkable advances recently:

• National Ignition Facility (NIF) achieved fusion ignition for the seventh time in February 2025, setting a new energy gain record of 2.44x. In April 2025, they produced a record fusion yield of 8.6 MJ - that’s more than four times the laser energy put in (2.08 MJ).
• Global investment has surged: Fusion startups have raised over $13 billion to date, with 17 companies having raised $100M+ each.

---

Biggest Hurdles & Challenges

1. Materials Science

The fusion environment is extremely hostile. Neutrons from fusion reactions will bombard the reactor’s first wall and vacuum vessel with more than 10 displacements per atom (dpa) per year, causing:

• Severe material degradation
• Tritium retention issues
• Erosion of plasma-facing components This requires entirely new materials that can withstand decades of operation.

2. Engineering Scale-Up

Moving from physics experiments to power plants presents enormous engineering challenges:

• For inertial confinement (NIF), you’d need to ignite pellets many times per second—described as a “dizzying” challenge
• Maintaining stable plasma at 150+ million°C for continuous operation (not just short pulses)
• Heat extraction systems that can convert fusion heat into electricity efficiently

3. Plasma Physics

Understanding and controlling plasma turbulence, instabilities, and confinement remains an ongoing science challenge. While tokamaks are proven, consistent, optimal performance is difficult.

4. Tritium Breeding

Fusion reactors need tritium (which is rare), so they must breed their own in the reactor blanket—a technology that hasn’t been demonstrated at commercial scale yet.

5. Cost & Complexity

Current fusion devices cost billions to build and operate. Economic competitiveness with other energy sources (and fission) remains uncertain.

---

Next Steps & Timeline

Public Research:

• ITER (the international tokamak project): Construction is progressing but the first plasma has been pushed back to 2034, a 9-year delay from earlier plans. Full deuterium-tritium operations are targeted for 2036+
• NIF: Continuing experiments with higher yields, working toward more efficient ignition schemes

Near-term Goals (2025-2030):

• SPARC tokamak (Commonwealth Fusion Systems) aims to demonstrate net energy by mid-2020s using new HTS magnets
• Continued NIF physics campaigns to understand ignition optimization
• DEMO reactor design work for next-generation demonstrations

Commercial Timeline:

The Fusion Industry Association states that the majority of fusion companies anticipate commercial power by the mid-2030s. This seems aggressive but reflects accelerated progress and massive investment.

---

Private Sector Research: How Promising?

The private sector is arguably making the most exciting progress:

Major Players:

• Commonwealth Fusion Systems (CFS): Developing SPARC using high-temperature superconducting magnets to create a compact, cheaper tokamak. They’ve already built and tested their HTS magnet technology at MIT’s Alcator C-Mod and are raising capital for the full SPARC device.

• Helion Energy: Pursuing a unique pulsed magnetic fusion approach (not a tokamak), planning a pilot plant by mid-decade with backing from Amazon’s Jeff Bezos and Bill Gates.

• Tae Technologies: Founded by John Nuckolls (NIF physicist) and others, using an inertial electrostatic confinement concept.

• 17 startups have each raised $100M+, collectively attracting over $13B in total investment.

Strengths of Private Research:

• Speed: Smaller, more focused teams can iterate faster than billion-dollar international projects like ITER
• Innovation: Willingness to pursue alternative approaches beyond tokamaks (stellarators, field-reversed configurations, laser-based ICF)
• Funding momentum: Strong VC interest and tech billionaire backing
• Regulatory progress: The ADVANCE Act (passed 2024 in the US) creates a more favorable regulatory framework for fusion

Concerns:

• Overhyped timelines (“commercial by mid-2030s” may be optimistic given historical nuclear project delays)
• Many companies will likely fail; it’s an unproven industry
• The “10-year away” phenomenon has plagued fusion for 60 years—can private sector avoid this?

---

Bottom Line

Nuclear fusion is in the most promising phase of its history. We’ve definitively proven scientific net energy (NIF), new technologies like HTS magnets are enabling smaller reactors, and private investment is unprecedented. However, the gap between “net energy in a lab experiment” and “reliable, economic electricity on the grid” remains massive—possibly 15-20 years still.

The consensus seems to be: fusion might reach early commercial deployment by the mid-2030s from private companies, but widespread adoption is likely decades away. Whether that’s good enough depends on your patience and how you weigh potential reward against current climate urgency.