Apple Silicon for Local LLMs — what to buy in October 2026

By LLM Hardware team · Methodology ·

Model fit and Mac prices rechecked 13 October 2026

Key facts

Qwen3.8-27B
Q4 formula 18.2 GB. Tight on 24 GB unified once macOS is counted. 36 GB Studio is the comfortable Mac.
Gemma 4
E2B/E4B for smaller Macs. 26B-A4B formula is 17.1 GB on 25.2B total, same 24 vs 36 GB split.
Prices
M4 Pro new buy box was not confirmed.
Not a mini
Kolibri-1 is ~78 GB FP8. Card minimum is H200/B200 class or two A100/H100s.

Checked 2026-10-13. Author: LLM Hardware team. Amazon prices are not stored or shown on this site.

Citeable facts

Key fact: A 24 GB Mac is tight for Qwen3.8-27B at Q4. A 36 GB Studio is the comfortable Apple fit. LFM2.5-24B-A2B Q4 is 16.4 GB and is tight on 24 GB unified.

How we got it: 27 × 0.5 × 1.2 + 2 = 18.2 GB. 24 × 0.5 × 1.2 + 2 = 16.4 GB. Subtract about 4 GB for macOS before judging the fit.

Checked:

Key fact: Gemma 4 26B-A4B needs 17.1 GB at Q4 when counted at 25.2B total parameters.

How we got it: 25.2 × 0.5 × 1.2 + 2. Google card: 3.8B active does not shrink the resident experts. Unsloth’s 4-bit note is 16–18 GB.

Checked:

Key fact: On a MacBook Pro with M5 Pro or M5 Max, 64 GB is the first memory option that holds a 70B model at Q4 with room for context; 48 GB holds it only at the edge, and only the 128 GB M5 Max holds a 70B model at Q8.

How we got it: 70 x 0.5 x 1.2 + 2 = 44.0 GB against 44 GB usable on 48 GB and 60 GB usable on 64 GB (memory less the 4 GB macOS reserve). 70 x 1.0 x 1.2 + 2 = 86.0 GB against 124 GB usable on 128 GB. Memory options from Apple's MacBook Pro with PROLED XDR Display tech specs.

Checked:

Methodology explains the VRAM formula, the bytes per weight at each quantization, and the full source list.

Unified memory is still the reason to buy a Mac for local models: the GPU can use the same pool as the CPU, so capacity matters more than a discrete VRAM ceiling. What changed by 1 October 2026 is which Macs Amazon had in stock. The in-stock Apple path tops out at 36GB. Anything at 64GB or above — including M5 Ultra — is an Apple Store configure, and this guide does not invent an ASIN for it.

Apple's current Mac mini comes with two chips. The M6 starts at 16 GB of unified memory and can be ordered with 24 GB or 32 GB. It is the same chip at every size, but the bandwidth changes with the memory: Apple lists 153 GB/s for the 16 GB model and 170 GB/s for the 24 GB and 32 GB models. The M5 Pro starts at 24 GB and goes to 48 GB or 64 GB, at 307 GB/s. The M4 models are now the previous generation.

For local models, the memory tier decides what fits. We hold back 4 GB for macOS, so a 16 GB M6 leaves about 12 GB for the model and a 32 GB M6 leaves about 28 GB. By our formula, a 14B model at Q4 needs about 10.4 GB, a 27B about 18.2 GB, a 32B about 21.2 GB and a 70B about 44 GB. That puts a 14B on the 16 GB M6, and a 27B at Q4 on the 32 GB M6 with room left for context. A 70B at Q4 would use all of a 48 GB M5 Pro's usable memory, so it needs a 64 GB M5 Pro or a Mac Studio.

The 16 GB and 24 GB M6 models are sold on Amazon. The 32 GB M6, the 48 GB and 64 GB M5 Pro and the Mac Studio builds are ordered from Apple.

Ranked buy-now

  1. 1. Apple Mac mini (M6, 16GB)

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

    Model fit. 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.

    Check current price on Amazon
  2. 2. Apple Mac mini (M6, 24GB)

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

    Model fit. 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.

    Check current price on Amazon
  3. 3. Apple Mac Studio (M5 Max, 36GB)

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

    Model fit. 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.

    Check current price on Amazon
  4. 4. Apple Mac mini (M5 Pro, 24GB)

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

    Model fit. 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.

    Check current price on Amazon
  5. 5. GMKtec EVO-X2 (Ryzen AI Max+ 395, 128GB)

    In stock (2026-10-17).

    Model fit. 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.

    Check current price on Amazon

Catalog entries live on the hardware index. Compare any two of them on the compare page. Check a specific model’s footprint with the VRAM calculator.

Memory tiers and the models that match them

The names in this table were mapped on 1 October and the Qwen3.8 / Gemma 4 cells were recalculated on 3 October with our VRAM formula. DeepSeek-V4-Flash, GLM-5.3-Flash, and the other large MoEs stay in the 96 GB-and-up rows. They are not 24 GB models. No new llama-bench run was done for this pass.

Memory tierHardware in this checkExample models
6–12 GB usable Mac mini M6 16GB. M4-era 16GB minis are the previous generation and are not a buy pick. K2-Horizon-0.9B, 3.7B, and 7B at Q4–Q5. Leave about half the 16GB pool for the OS.
16–24 GB Mac mini M6 24GB and Mac mini M5 Pro 24GB. Mac Studio M5 Max 36GB is the top of this band. Qwen3.8-27B Q4 is 18.2 GB by the formula (Ollama listed 18 GB). Tight on 24 GB unified, comfortable on 36 GB. Gemma 4 26B-A4B is 17.1 GB on 25.2B total, same split. Gemma 4 E2B/E4B fit the smaller end of this band.
48–64 GB M5 Pro 48GB and 64GB, Mac Studio M5 Max, and MacBook Pro with M5 Pro or M5 Max at 48GB or 64GB, ordered from Apple. M4-era machines in this band are the previous generation and are not a buy pick. Qwen3.8-27B at higher precision, K2-Horizon-32B with room, and small MoE experiments. 70B-class MoE only at aggressive quants.
96–128 GB GMKtec EVO-X2 128GB. Mac Studio M5 Ultra and the 128GB MacBook Pro M5 Max are ordered from Apple. Qwen3.8-Flash-Next UD-IQ4_XS is 93.68 GB and fits 128 GB. It does not fit the 96 GB M5 Ultra base once macOS is reserved. UD-Q4_K_XL is 111.33 GB and is tight on 128 GB and does not fit 96 GB. A 70B Q4 file is 44 GB and fits the 96 GB Ultra. DeepSeek-V4-Flash at a normal 4-bit is about 155 GB and does not fit either box.
192 GB+ Apple Ultra 256–512GB on the Apple configure page. Framework Desktop 192GB showed up in community discussion and was not Amazon-verified in this Mac pass. DeepSeek-V4.1-Flash at low bits, GLM-5.3-Flash, MiniMax-M3, and larger MoEs.

MacBook Pro with M5 Pro or M5 Max: memory tiers

Apple announced a MacBook Pro with a PROLED XDR Display on 28 October 2026, in 14-inch and 16-inch sizes, with M5 Pro or M5 Max. Apple's press release says pre-orders opened that day, with availability beginning Friday, 6 November. The options below are from Apple's tech specs page, read on 1 November 2026. Apple's main MacBook Pro specs page lists the same M5 Pro and M5 Max memory and bandwidth for the Liquid Retina XDR model, so the table applies to both. Our hardware catalog has no MacBook Pro, so there is no buy link here.

Memory decides what fits. Bandwidth is Apple's figure for comparing chips; it does not change the fit. As in the rest of this guide, we hold back 4 GB for macOS. Sizes use the site formula, parameters x bytes per parameter x 1.2 + 2 GB, at a short context. Fits means at least 10% of the usable memory is left; tight means the model fits inside the last 10%, with little room for a longer chat.

MemoryChip and bandwidthUsable after 4 GBFitsTightDoes not fit
24 GBM5 Pro, 307 GB/s20 GB8B Q4 (6.8 GB), 8B Q8 (11.6 GB), 14B Q4 (10.4 GB)27B Q4 (18.2 GB), 14B Q8 (18.8 GB)32B Q4 (21.2 GB)
36 GBM5 Max with 32-core GPU, 460 GB/s32 GB27B Q4 (18.2 GB), 32B Q4 (21.2 GB), 14B Q8 (18.8 GB)None of these sizes27B Q8 (34.4 GB), 70B Q4 (44.0 GB)
48 GBM5 Pro, 307 GB/s, or M5 Max with 40-core GPU, 614 GB/s44 GB27B Q8 (34.4 GB), 14B FP16 (35.6 GB)32B Q8 (40.4 GB), 70B Q4 (44.0 GB, no room left for context)70B Q8 (86.0 GB)
64 GBM5 Pro with 20-core GPU, 307 GB/s, or M5 Max with 40-core GPU, 614 GB/s60 GB70B Q4 (44.0 GB), 32B Q8 (40.4 GB)None of these sizes27B FP16 (66.8 GB), 70B Q8 (86.0 GB)
128 GBM5 Max with 40-core GPU, 614 GB/s124 GB70B Q8 (86.0 GB), 32B FP16 (78.8 GB), a 120B mixture of experts at Q4 (74.0 GB on total parameters)None of these sizes70B FP16 (170.0 GB)

The step that changes what you can run is 64 GB: it is the first option that holds a 70B model at Q4 with room for context. At 48 GB the same model fills all of the usable memory. Only the 128 GB M5 Max holds a 70B model at Q8.

Apple's press release says: "With M5 Max, pros can run LLMs with hundreds of billions of parameters entirely on device." That is Apple's claim. By the site formula at Q4, the 128 GB configuration holds a model of about 180B parameters with the 10% headroom (180 x 0.5 x 1.2 + 2 = 110.0 GB) and about 200B at the edge (122.0 GB). Larger models need a smaller quant than Q4, which this guide does not size. Check a specific model in the VRAM calculator, and see How to run LLMs on Mac for setup.

AI and automation help produce this content; every figure is checked against the cited sources and the site formula before publishing.

Not on Amazon — configure at Apple

If the model you care about is a large MoE, the in-stock Studio is the wrong box. These configs were on Apple’s buy page and did not have a US Amazon ASIN we could verify. An EU tracker ASIN (B0HGRN2PV2) returned 404 on amazon.com, so it is not listed.

Start at apple.com/shop/buy-mac/mac-studio. The 36GB M5 Max base is also sold on Amazon; the higher memory steps are the Apple-only part.

Watchlist, not buy-now

Strix Halo when the Mac memory ceiling is the problem

Community discussion in September and October 2026 kept pointing at high unified memory — Studio M5 Max and Ultra, Strix Halo 128GB, Framework Desktop 192GB — for Qwen3.8, Flash-Next, and Muse. The default Amazon PC in that class is the GMKtec EVO-X2: 128 GB at about 256 GB/s. The Beelink GTR9 Pro is the same APU and bandwidth with a higher price and a 10GbE NIC history; it is a caveat on the Strix Halo guide, not a second default. Plan on Linux or a ROCm/Vulkan stack. CUDA workflows still belong on an NVIDIA card; see the GPU buying guide and the Mac vs PC guide.

DeepSeek’s current big local target in this window is DeepSeek-V4-Flash (~155GB at a normal 4-bit). That is an EVO-X2 aggressive quant or an Apple Ultra, not a 24GB mini. Qwen sizing for the dense 27B class is covered in the Qwen hardware guide.

How to run whatever you buy

On the Macs, Ollama is the always-on worker (brew install ollama, then a model pull). For the 3 October models the tags are ollama run qwen3.8:27b and ollama run gemma4:26b on a 36 GB Studio, and gemma4:e4b or gemma4:e2b when the pool is smaller. There is also a qwen3.8:27b-mlx tag if you want the MLX build Ollama listed. LM Studio is the GUI. llama.cpp with Metal is the same engine with the flags exposed. MLX (pip install mlx-lm) is Apple’s framework and the one to reach for when you want to fine-tune on the GPU you already bought. Setup steps are in How to run LLMs on Mac and the Ollama cheat sheet. Check the number first in the VRAM calculator. The quantization trade itself is in the quantization guide and how much VRAM you need. The tier that says “does not fit 16 GB” is on what you can run.

A Mac mini in this tier is a reasonable always-on machine for agents and a self-hosted runner. It is not a substitute for 64GB+ when the weights do not fit. Memory is soldered. Buy the pool you need on day one.

Frequently asked questions

Which Mac should I buy on Amazon for local LLMs in October 2026?

Qwen3.6-27B Q4 is 18.2 GB: tight on 24 GB unified, comfortable on the 36 GB Studio. LFM2.5-24B-A2B Q4 is 16.4 GB: tight on 24 GB unified after a ~4 GB reserve, and it fits the 36 GB Studio. Q8 is 30.8 GB and is the edge of 36 GB after that reserve. Qwen3.8-Flash-Next UD-Q4_K_XL is 111.33 GB and fits neither Mac. The M5 Ultra 96GB base is an Apple configure with no verified US dollar and no Amazon ASIN. After a 4 GB macOS reserve it holds a 70B Q4 file (44 GB) and does not hold Flash-Next (110 GB).

What models fit a 24GB or 36GB Mac at Q4?

Our VRAM formula is params × bytes × 1.2 + 2. Qwen3.8-27B at Q4 is 18.2 GB, and Ollama listed an 18 GB download on 3 October 2026. That fits a 24 GB discrete GPU at a short context and is tight on a 24 GB Mac because macOS shares the pool. A 36 GB Mac Studio M5 Max is the comfortable Mac for that model and for Gemma 4 26B-A4B (17.1 GB on its 25.2B total). Skip 32B Q8 (40.4 GB) on both. It is not a DeepSeek-V4-Flash machine, and it is not a Kolibri machine.

Can I buy a 64GB or Ultra Mac Studio on Amazon?

Not as a verified in-stock Amazon buy on 2026-10-01. The Mac Studio M4 Max 64GB/1TB listing (ASIN B0FNS1ZX5B) was currently unavailable. 48GB Mac mini M4 Pro listings (B0DS2XP86K and B0DYFCQ7CB) were also unavailable. M5 Max 64GB and M5 Ultra 96GB are configured at apple.com/shop/buy-mac/mac-studio. This guide does not invent Amazon ASINs for those configs.

Why is the GMKtec EVO-X2 on a Mac guide?

It is the verified Amazon PC alternative when unified memory above 64GB is the goal. The EVO-X2 (Ryzen AI Max+ 395, Strix Halo) has 128GB soldered LPDDR5X at about 256 GB/s. Qwen3.8-Flash-Next UD-IQ4_XS is 93.68 GB and fits. UD-Q4_K_XL is 111.33 GB and is tight. A dense 70B Q4 is 44 GB and is slow at this bandwidth. The old GTR9 ASIN B0GQXDCKN1 loaded a Beelink SER3 that day, so it is not a buy link. The EVO-X2 is not CUDA.

Does Gemma 4 or Kolibri change which Mac to buy?

Gemma 4 E2B and E4B fit smaller Macs. Unsloth’s Q4_K_M files were 3.11 GB and 4.98 GB on 3 October 2026. Gemma 4 26B-A4B is 25.2B total and 3.8B active, Apache-2.0, and the Q4 formula on the total is 17.1 GB, so it follows the same 24 GB tight / 36 GB comfortable split as Qwen3.8-27B. Kolibri-1 does not change a consumer Mac purchase. Aleph Alpha’s card lists about 78 GB of FP8 weights and a minimum of datacenter GPUs (two A100 80 GB or two H100s, or one H200, B200, or B300). That is not a 24 GB mini and not a claim that a 128 GB box matches their tested stack.

What tools run local LLMs on Apple Silicon?

Ollama, LM Studio, llama.cpp with Metal, and Apple MLX all run on Apple Silicon. Ollama is the usual always-on worker. MLX is the path when you want Apple’s own framework, including fine-tuning experiments. None of these replace buying enough unified memory for the model.

Which MacBook Pro memory option do I need for a 70B model?

64 GB. By the site formula a 70B model at Q4 is 44.0 GB. After the 4 GB macOS reserve, a 64 GB MacBook Pro (M5 Pro with the 20-core GPU, or M5 Max with the 40-core GPU) has 60 GB usable, so the model fits with room for context. The 48 GB option has 44 GB usable, so the model fills all of it. For a 70B model at Q8 (86.0 GB), only the 128 GB M5 Max fits.

Check a model against these machines, or compare them side by side.

Sources

A number that does not match a listing? Contact us.