Hardware for Local LLMs

Specs for 32 GPUs and Apple Silicon devices stay on this page. Separate per-SKU URLs were consolidated here for good — they return 410 and are not coming back.

All 32 GPUs, mini PCs, and Apple Silicon devices tracked for local AI inference. Use the VRAM calculator to see which models fit each device, or open the compare table. Kept guides such as the RTX 4090 LLM guide stay on their own URLs.

NVIDIA GPUs

NVIDIA GeForce RTX 4060 (8GB)

8 GB VRAM ~272 GB/s 115W Check current price on Amazon

Buy New, only 1 left (2026-10-17). Seller name was not in the parsed buy box.

Check VRAM fit Buy on Amazon

NVIDIA GeForce RTX 4070 (12GB)

12 GB VRAM ~504 GB/s 200W Check current price on Amazon

In stock, only 9 left (2026-10-17).

Check VRAM fit Buy on Amazon

NVIDIA GeForce RTX 4090 (24GB)

24 GB VRAM ~1008 GB/s 450W Check current price on Amazon

Currently unavailable (2026-10-17).

Check VRAM fit Buy on Amazon

NVIDIA GeForce RTX 3090 (24GB)

24 GB VRAM ~936 GB/s 350W Check current price on Amazon

24 GB fits Llama 3.1 8B Q4 (6.8 GB) and Qwen3.6-27B Q4 (18.2 GB). 70B Q4 is 44 GB and does not fit.

Buy New, only 1 left (2026-10-17).

Check VRAM fit Buy on Amazon

NVIDIA GeForce RTX 5090 (32GB)

32 GB VRAM ~1792 GB/s 575W Check current price on Amazon

Currently unavailable. See All Buying Options (2026-10-17).

Check VRAM fit Buy on Amazon

NVIDIA RTX 4080 (16GB)

16 GB VRAM ~716 GB/s 320W Check current price on Amazon

Only 1 left (2026-10-17).

Check VRAM fit Buy on Amazon

NVIDIA RTX 4060 Ti (16GB)

16 GB VRAM ~288 GB/s 165W Check current price on Amazon

Currently unavailable (2026-10-17).

Check VRAM fit Buy on Amazon

NVIDIA RTX 5080 (16GB)

16 GB VRAM ~960 GB/s 360W Check current price on Amazon

17 October 2026 page mixed a remaining-count line with an unavailable widget. Prior observation not replaced.

Check VRAM fit Buy on Amazon

NVIDIA RTX 5070 (12GB)

12 GB VRAM ~672 GB/s 250W Check current price on Amazon

In stock, sold by Amazon.com (2026-10-17).

Check VRAM fit Buy on Amazon

NVIDIA RTX 5070 Ti (16GB)

16 GB VRAM ~896 GB/s 300W Check current price on Amazon

Only 1 left (2026-10-17).

Check VRAM fit Buy on Amazon

NVIDIA RTX 4070 Ti Super (16GB)

16 GB VRAM ~672 GB/s 285W Check current price on Amazon

Buy Used from Hcir Equipment, 8 left (2026-10-17). Not a new buy box.

Check VRAM fit Buy on Amazon

NVIDIA DGX Spark

128 GB VRAM ~273 GB/s 170W Check current price on Amazon

Currently unavailable (2026-10-17).

Check VRAM fit Buy on Amazon

PNY GeForce RTX 5060 Ti (16GB)

16 GB VRAM ~448 GB/s 180W Check current price on Amazon

Currently unavailable (2026-10-17). No new price.

Check VRAM fit Buy on Amazon

AMD GPUs

AMD Radeon RX 7900 XTX (24GB)

24 GB VRAM ~960 GB/s 355W Check current price on Amazon

Currently unavailable (2026-10-17).

Check VRAM fit Buy on Amazon

Intel GPUs

Intel Arc B580 (12GB)

12 GB VRAM ~456 GB/s 190W Check current price on Amazon

Availability line blank (2026-10-17).

Check VRAM fit Buy on Amazon

Apple Silicon

Apple Mac mini (M6, 16GB)

16 GB unified ~153 GB/s Check current price on Amazon

After a 4 GB macOS reserve, about 12 GB is usable. 7B Q4 is 6.2 GB and fits. 8B Q4 is 6.8 GB and fits. Gemma 3 12B Q4 is 9.2 GB and fits with little room. 14B Q4 is 10.4 GB and is tight. 27B Q4 is 18.2 GB and does not fit.

In stock, sold by Amazon.com (2026-10-18).

Check VRAM fit Buy on Amazon

Apple Mac mini (M6, 24GB)

24 GB unified ~170 GB/s Check current price on Amazon

After a 4 GB macOS reserve, about 20 GB is usable. 14B Q4 is 10.4 GB and fits. 27B Q4 is 18.2 GB and is tight. 32B Q4 is 21.2 GB and does not fit.

Sold by Amazon.com. Usually ships within 3 to 5 weeks (2026-10-18).

Check VRAM fit Buy on Amazon

Apple Mac Studio (M5 Max, 36GB)

36 GB unified ~460 GB/s Check current price on Amazon

After a 4 GB macOS reserve, about 32 GB is usable. Qwen3.6-27B Q4 is 18.2 GB and fits. LFM2.5-24B-A2B Q4 is 16.4 GB and fits. Q8 is 30.8 GB and is the edge. 70B Q4 is 44 GB and does not fit.

In stock, Amazon.com (2026-10-17).

Check VRAM fit Buy on Amazon

Apple Mac mini (M5 Pro, 24GB)

24 GB unified ~307 GB/s Check current price on Amazon

After a 4 GB macOS reserve, about 20 GB is usable. 27B Q4 is 18.2 GB and is tight. LFM2.5-24B-A2B Q4 is 16.4 GB and is tight. Q8 is 30.8 GB and does not fit.

In stock, Amazon.com (2026-10-17).

Check VRAM fit Buy on Amazon

Apple Mac mini (M4, 16GB)

16 GB unified ~120 GB/s 25W Check current price on Amazon

After a 4 GB macOS reserve, about 12 GB is usable. 7B Q4 is 6.2 GB and fits. 14B Q4 is 10.4 GB and is tight. 27B Q4 is 18.2 GB and does not fit.

Price needs re-check (no clean buy box, 2026-10-01)

Apple Mac mini (M4, 24GB)

24 GB unified ~120 GB/s 25W Check current price on Amazon

After a 4 GB macOS reserve, about 20 GB is usable. 14B Q4 is 10.4 GB and fits. 27B Q4 is 18.2 GB and is tight. 32B Q4 is 21.2 GB and does not fit.

Price needs re-check (no clean buy box, 2026-10-01)

Apple Mac mini (M4 Pro, 24GB)

24 GB unified ~273 GB/s 35W Check current price on Amazon

After a 4 GB macOS reserve, about 20 GB is usable. 27B Q4 is 18.2 GB and is tight. LFM2.5-24B-A2B Q4 is 16.4 GB and is tight. Q8 is 30.8 GB and does not fit.

No confirmed new buy box (2026-10-11).

Apple Mac mini (M4 Pro, 48GB)

48 GB unified ~273 GB/s 40W Check current price on Amazon

After a 4 GB macOS reserve, about 44 GB is usable. 27B Q8 is 34.4 GB and fits. 70B Q4 is 44 GB and is the edge. 70B Q8 is 86 GB and does not fit.

Currently unavailable (2026-10-01)

Apple Mac Studio (M4 Max, 64GB)

64 GB unified ~546 GB/s 85W Check current price on Amazon

After a 4 GB macOS reserve, about 60 GB is usable. 70B Q4 is 44 GB and fits. 27B FP16 is 66.8 GB and does not fit. 70B Q8 is 86 GB and does not fit.

Currently unavailable (2026-10-01)

Apple Mac Studio (M4 Max, 128GB)

128 GB unified ~546 GB/s 85W Check current price on Amazon

After a 4 GB macOS reserve, about 124 GB is usable. 70B Q8 is 86 GB and fits. Qwen3.8-Flash-Next UD-Q4_K_XL is 111.33 GB and is tight.

Price not re-checked (2026-10-01) — configure 64GB+ at Apple

Apple Mac Studio (M5 Max, 48GB)

48 GB unified ~614 GB/s Check current price on Amazon

After a 4 GB macOS reserve, about 44 GB is usable. 27B Q8 is 34.4 GB and fits. 70B Q4 is 44 GB and is the edge. 70B Q8 is 86 GB and does not fit.

Apple Mac Studio (M5 Max, 64GB)

64 GB unified ~614 GB/s Check current price on Amazon

After a 4 GB macOS reserve, about 60 GB is usable. 70B Q4 is 44 GB and fits. 27B FP16 is 66.8 GB and does not fit. 70B Q8 is 86 GB and does not fit.

Apple Mac Studio (M5 Max, 128GB)

128 GB unified ~614 GB/s Check current price on Amazon

After a 4 GB macOS reserve, about 124 GB is usable. 70B Q8 is 86 GB and fits. Qwen3.8-Flash-Next UD-Q4_K_XL is 111.33 GB and is tight.

Apple Mac Studio (M5 Ultra, 96GB)

96 GB unified ~1200 GB/s Check current price on Amazon

After a 4 GB macOS reserve, about 92 GB is usable. 70B Q4 is 44 GB and fits. 70B Q8 is 86 GB and is tight. Nemotron 3.5 Bolt at Q4 is 46.4 GB and fits. Qwen3.8-Flash-Next UD-Q4_K_XL is 111.33 GB and does not fit.

Mini PCs

GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB)

128 GB unified ~256 GB/s 140W Check current price on Amazon

128 GB at ~256 GB/s. Dense 70B Q4 (44 GB) fits and is slow. Qwen3.8-Flash-Next UD-IQ4_XS is 93.68 GB and fits. UD-Q4_K_XL is 111.33 GB and is tight. DeepSeek-V4-Flash only at an aggressive quant (~155 GB at a normal 4-bit). Not CUDA.

In stock (2026-10-17).

Check VRAM fit Buy on Amazon

Beelink GTR9 Pro (128GB) — out of stock

128 GB unified ~256 GB/s Check current price on Amazon

128 GB at ~256 GB/s when the listing is this GTR9 Pro. UD-IQ4_XS (93.68 GB) fits. UD-Q4_K_XL (111.33 GB) is tight. Sold out on 2026-10-11. Not CUDA.

Beelink GTR9 Pro (128GB, OOS watchlist)

128 GB unified ~256 GB/s Check current price on Amazon

Same 128 GB / ~256 GB/s tier when stocked. UD-IQ4_XS (93.68 GB) fits. Not a buy on 2026-10-09.

Currently unavailable (2026-10-11). No buy box.

Browse All Models All Guides Compare GPUs VRAM Calculator

Sources & last reviewed

Last reviewed October 18, 2026 by the LLM Hardware team. The date changes only when the numbers or sources on this page change.

Vendor spec pages (VRAM / unified memory)

NVIDIA GeForce RTX 5090 specs — 32 GB GDDR7.
NVIDIA GeForce RTX 5080 specs — 16 GB GDDR7.
NVIDIA GeForce RTX 5070 family specs — RTX 5070 12 GB, RTX 5070 Ti 16 GB.
NVIDIA GeForce RTX 4090 specs — 24 GB GDDR6X.
NVIDIA GeForce RTX 4060 family specs — RTX 4060 Ti 16 GB / 8 GB, RTX 4060 8 GB.
NVIDIA GeForce RTX 3090 / 3090 Ti specs — 24 GB GDDR6X on both cards.
AMD Radeon RX 7900 XTX specs — 24 GB GDDR6.
AMD Radeon RX 9070 XT specs — 16 GB GDDR6.
AMD Ryzen AI Max+ 395 specs — up to 128 GB shared memory (Strix Halo mini PCs).
Apple Mac Studio tech specs — M5 Max 32-core GPU 36GB at 460GB/s; M5 Max 40-core GPU at 614GB/s for 48GB, 64GB, or 128GB; M5 Ultra 96GB at 1.2TB/s (checked 2026-10-18).
Apple Mac mini tech specs — M6 16GB at 153GB/s; M6 24GB and 32GB at 170GB/s; M5 Pro 24GB at 307GB/s, configurable to 48GB or 64GB (checked 2026-10-18).

Model cards used for the fit tiers

Qwen/Qwen3-8B model card (Hugging Face) — 8.2B parameters, 32,768-token native context; the 8B row.
Qwen/Qwen3-14B model card (Hugging Face) — 14.8B parameters; the 14B row.
Qwen/Qwen3-32B model card (Hugging Face) — 32.8B parameters, 32,768-token native context; the 32B row.
meta-llama/Llama-3.3-70B-Instruct model card (Hugging Face) — 70B parameters; the 70B row (44 GB at Q4).

VRAM estimates use params × bytes per parameter × 1.2 + 2 GB (Q4_K_M ≈ 0.5 bytes), explained on the methodology page. Found a mismatch? Tell us on the contact page.