LocalLLMChecker

Unified memory · Apple

What AI models can an Apple M3 Max 48GB run?

48 GB puts the 70B class within comfortable reach and leaves room for the context window that makes those models worth running. Memory is shared with the CPU, so the practical ceiling is lower than the sticker number: macOS hands roughly three quarters of it to the GPU by default.

Memory48 GB
Bandwidth400 GB/s
Usable for a model36 GB
Runtime backendMETAL

The short answer

Assuming an 8k context window and default settings, these are the models worth downloading first.

Best all-rounder

Gemma 4 26B A4B Instruct

Q8_0 · 26.69 GB · about 34.9 tokens/s

Best for code

Qwen3 32B

Q6_K · 27.43 GB · about 10.3 tokens/s

Largest that still runs well

Qwen3 32B

32.76B parameters · Q6_K · about 10.3 tokens/s

Fastest useful answer

LFM2.5 8B A1B

about 95.7 tokens/s · 8.78 GB

See how fast it feels

Apple M3 Max 48GB running Gemma 4 26B A4B Instruct at Q8_0

Wait for the first word898 ms
Then writes at34.9 tok/s
Whole answer5.9 s

YouWhy does my model use more memory when the conversation gets longer?

Model

Simulated from our estimate at a 512-token question, not a recording. Assumes nothing else is competing for the GPU.

Where it sits

The GPU can use about 36 GB of this machine's 48 GB by default, so for planning it behaves like a 32 GB card with different bandwidth. The 32 GB guide explains what that tier runs and where it runs out, and the bandwidth guide explains why 400 GB/s decides how fast it answers.

Our indicative price for this machine is $3,299 new, reviewed 2026-09-01. That is 1.5 GB of memory and 12 GB/s of bandwidth for every $100. Prices move, so treat these as a place to start a search and not a quote.

Devices in a similar price band, fastest memory first:

DevicePriceMemoryBandwidthBest all-round pick
Apple M3 Ultra 96GB $3,999 96 GB 819 GB/s GPT OSS 120B, 102.5 t/s
Apple M1 Ultra 128GB $3,400 128 GB 800 GB/s GPT OSS 120B, 100.1 t/s
Apple M2 Ultra 64GB $3,499 64 GB 800 GB/s Qwen3.5 27B, 20.2 t/s
Apple M4 Max 36GB $3,199 36 GB 546 GB/s Gemma 4 12B Instruct, 28.2 t/s

Every model, scored on this device

Each row uses the highest-quality quantization that both fits and stays conversational. Speed is a single-stream estimate at 8k context.

Model Params Verdict Download Memory used Speed Max context
Gemma 4 26B A4B Instruct
Gemma 		25.81B (3.74B active) Runs great Q8_0 26.69 GB 34.9 t/s 64k
GLM 4.7 Flash
GLM 		31.22B (3.66B active) Runs great Q8_0 31.61 GB 39.5 t/s 64k
Gemma 4 31B Instruct
Gemma 		31.27B Runs well Q6_K 27.58 GB 10 t/s 32k
Qwen3 30B A3B
Qwen 		30.53B (3.34B active) Runs great Q8_0 31.27 GB 39.2 t/s 32k
Gemma 4 12B Instruct
Gemma 		11.96B Runs well Q8_0 13.52 GB 20.7 t/s 128k
Qwen3 32B
Qwen 		32.76B Runs well Q6_K 27.43 GB 10.3 t/s 32k
GPT OSS 20B
GPT-OSS 		20.91B (4.18B active) Runs great MXFP4 11.81 GB 66 t/s 128k
Qwen3.5 27B
Qwen 		27.78B Runs well Q8_0 28.54 GB 10.1 t/s 64k
Qwen3 Coder 30B A3B Instruct
Qwen 		30.53B (3.34B active) Runs great Q8_0 31.27 GB 39.2 t/s 32k
Qwen3 14B
Qwen 		14.77B Runs well Q8_0 16.28 GB 18 t/s 32k
Granite 4.1 30B
Granite 		28.87B Runs well Q6_K 24.42 GB 11.3 t/s 32k
Qwen3.5 9B
Qwen 		9.65B Runs great Q8_0 10.22 GB 30.8 t/s 256k
Qwen2.5 14B Instruct
Qwen 		14.77B Runs well Q8_0 16.53 GB 17.7 t/s 32k
Qwen2.5 32B Instruct
Qwen 		32.76B Runs well Q6_K 27.43 GB 10.3 t/s 32k
Gemma 3 27B Instruct
Gemma 		27.43B Runs well Q6_K 22.45 GB 12.3 t/s 128k
Qwen2.5 Coder 14B Instruct
Qwen 		14.77B Runs well Q8_0 16.53 GB 17.7 t/s 32k
Qwen2.5 Coder 32B Instruct
Qwen 		32.76B Runs well Q6_K 27.43 GB 10.3 t/s 32k
Gemma 3 12B Instruct
Gemma 		12.19B Runs well Q8_0 13.24 GB 21.1 t/s 128k
Phi 4
Phi 		14.66B Runs well Q8_0 16.48 GB 17.5 t/s 16k
Gemma 4 E4B Instruct
Gemma 		8B Runs great Q8_0 8.39 GB 33.7 t/s 128k
Granite 4.1 8B
Granite 		8.79B Runs great Q8_0 10.32 GB 27.3 t/s 128k
Qwen3 8B
Qwen 		8.19B Runs great Q8_0 9.61 GB 31.6 t/s 32k
Mistral Nemo Instruct 2407
Mistral 		12.25B Runs well Q8_0 13.78 GB 21.4 t/s 128k
Qwen2.5 VL 7B Instruct
Qwen 		8.29B Runs great Q8_0 9 GB 33.6 t/s 64k
Mistral Small 24B Instruct 2501
Mistral 		23.57B Runs well Q8_0 24.98 GB 11.4 t/s 32k
Qwen2.5 7B Instruct
Qwen 		7.62B Runs great Q8_0 8.34 GB 36.6 t/s 32k
Llama 3.1 8B Instruct
Llama 		8.03B Runs great Q8_0 9.32 GB 32.3 t/s 128k
DeepSeek Coder V2 Lite Instruct
DeepSeek 		15.71B (2.74B active) Runs great Q8_0 16.09 GB 54.2 t/s 128k
Codestral 22B V0.1
Mistral 		22.25B Runs well Q8_0 24.21 GB 11.5 t/s 32k
Gemma 2 9B Instruct
Gemma 		9.24B Runs well Q8_0 11.47 GB 24.5 t/s 8k
Show the other 56 models
Qwen2.5 Coder 7B Instruct 7.62B Runs great Q8_0 8.34 GB 36.6 t/s 32k
OLMo 3 7B Instruct 7.3B Runs great Q8_0 10.1 GB 29.2 t/s 64k
Internlm3 8B Instruct 8.8B Runs great Q8_0 9.46 GB 31.8 t/s 32k
Mistral 7B Instruct V0.3 7.25B Runs great Q8_0 8.55 GB 33.8 t/s 32k
Gemma 4 E2B Instruct 5.12B Runs great Q8_0 5.41 GB 53.1 t/s 128k
Qwen3.5 4B 4.66B Runs great Q8_0 5.24 GB 55.4 t/s 256k
Mistral 7B Instruct V0.2 7.24B Runs great Q8_0 8.54 GB 33.8 t/s 32k
DeepSeek Coder 7B Instruct V1.5 6.91B Runs great Q8_0 10.96 GB 26.7 t/s 4k
DeepSeek Coder 6.7B Instruct 6.74B Runs great Q8_0 11.04 GB 25.8 t/s 16k
LFM2.5 8B A1B 8.47B Runs great Q8_0 8.78 GB 95.7 t/s 64k
Qwen3 4B 4.02B Runs great Q8_0 5.43 GB 53.3 t/s 32k
Gemma 3 4B Instruct 4.3B Runs great Q8_0 4.88 GB 59.7 t/s 128k
Qwen3.5 122B A10B 125.09B Fits only at 2 to 3 bits IQ2_XXS 30.67 GB 69.2 t/s 128k
Phi 4 Mini Instruct 3.84B Runs great Q8_0 5.14 GB 56.7 t/s 128k
Granite 4.1 3B 3.4B Runs great Q8_0 4.31 GB 68.2 t/s 128k
Qwen2.5 3B Instruct 3.09B Runs great Q8_0 3.65 GB 81.4 t/s 32k
Phi 3 Mini 4k Instruct 3.82B Runs great Q8_0 4.87 GB 61.4 t/s 4k
Llama 3.2 3B Instruct 3.21B Runs great Q8_0 4.39 GB 67.1 t/s 128k
LFM2.5 2.6B 2.7B Runs great Q8_0 3.11 GB 97.2 t/s 128k
Qwen3.5 2B 2.27B Runs great Q8_0 2.67 GB 115.3 t/s 256k
Gemma 2 2B Instruct 2.61B Runs great Q8_0 3.51 GB 85.2 t/s 8k
Starcoder2 3B 3.03B Runs great Q8_0 3.46 GB 91.7 t/s 16k
Qwen3 1.7B 2.03B Runs great Q8_0 3.19 GB 94.3 t/s 32k
DeepSeek R1 Distill Qwen 1.5B 1.78B Runs great Q8_0 2.27 GB 155.5 t/s 128k
Qwen2.5 1.5B Instruct 1.54B Runs great Q8_0 2.03 GB 156.1 t/s 32k
SmolLM2 1.7B 1.71B Runs great Q8_0 3.5 GB 85.2 t/s 8k
OLMo 2 0425 1B 1.48B Runs great Q8_0 2.77 GB 120.3 t/s 4k
Llama 3.2 1B Instruct 1.24B Runs great Q8_0 1.79 GB 184.1 t/s 128k
LFM2.5 1.2B Instruct 1.17B Runs great Q8_0 1.56 GB 243.1 t/s 64k
Gemma 3 1B Instruct 1B Runs great Q8_0 1.32 GB 261.8 t/s 32k
Qwen3.5 0.8B 0.87B Runs great Q8_0 1.25 GB 279.5 t/s 256k
Qwen3 0.6B 0.75B Runs great Q8_0 1.89 GB 168.2 t/s 32k
Qwen2.5 0.5B Instruct 0.49B Runs great Q8_0 0.85 GB 470 t/s 32k
LFM2.5 350M 0.35B Runs great Q8_0 0.71 GB 727.8 t/s 64k
Qwen3 Next 80B A3B Instruct 81.32B Just fits n/a 40.8 GB 86.1 t/s n/a
Qwen3 Coder Next 79.67B Just fits n/a 39.99 GB 86.1 t/s n/a
Qwen3.5 35B A3B 35.95B Just fits n/a 36.1 GB 51.8 t/s n/a
GLM 4.5 Air 110.47B Fits only at 2 to 3 bits n/a 41.17 GB 25.5 t/s n/a
Phi 3.5 MoE Instruct 41.87B Just fits n/a 42.81 GB 20.9 t/s n/a
Mixtral 8x7B Instruct V0.1 46.7B Just fits n/a 37.04 GB 14.6 t/s n/a
Qwen2.5 VL 72B Instruct 73.41B Just fits n/a 39.33 GB 7.1 t/s n/a
Llama 3.3 70B Instruct 70.55B Just fits n/a 42.68 GB 6.5 t/s n/a
Qwen2.5 72B Instruct 72.71B Just fits n/a 43.9 GB 6.4 t/s n/a
Llama 3 3 Nemotron Super 49B V1 49.87B Just fits n/a 43.21 GB 6.4 t/s n/a
GPT OSS 120B 116.83B CPU only n/a 59.65 GB n/a n/a
Kimi K2.6 1026.88B Will not run n/a 578.41 GB n/a n/a
Kimi K2 Instruct 1026.41B Will not run n/a 578.15 GB n/a n/a
GLM 5.1 753.86B Will not run n/a 425.01 GB n/a n/a
GLM 5.2 753.33B Will not run n/a 424.72 GB n/a n/a
DeepSeek V3.2 685.4B Will not run n/a 386.4 GB n/a n/a
DeepSeek R1 684.53B Will not run n/a 385.92 GB n/a n/a
MiniMax M3 427.04B Will not run n/a 241.5 GB n/a n/a
GLM 4.5 358.34B Will not run n/a 204.77 GB n/a n/a
Qwen3 235B A22B 235.09B Will not run n/a 134.03 GB n/a n/a
MiniMax M2.5 228.7B Will not run n/a 130.88 GB n/a n/a
MiniMax M2.7 228.69B Will not run n/a 130.87 GB n/a n/a

What it will not run

22 of the 86 architectures we track are out of reach here, even at 2-bit precision.

If you want more headroom

The next steps up in memory, in order. More memory changes which models load at all; more bandwidth changes how fast they answer, so the two are worth weighing separately.

DeviceMemoryBandwidthModels that fit
Ryzen AI Max+ 395 64GB 64 GB 256 GB/s 66 Check price
Jetson AGX Orin 64GB 64 GB 204.8 GB/s 66 Check price
RTX PRO 6000 Blackwell 96 GB 1792 GB/s 76 Check price
Ryzen AI Max+ 395 96GB 96 GB 256 GB/s 69 Check price

Price links go to an Amazon search for the model name and are affiliate links: if you buy through one, we earn a commission at no cost to you. We do not take payment for placement, and the ordering above is by memory capacity alone.

Other devices with 48 GB

Same capacity, different speed. Once a model fits, bandwidth is what separates these.

RTX 6000 Ada Generation

960 GB/s · NVIDIA

Radeon PRO W7900

864 GB/s · AMD

RTX A6000

768 GB/s · NVIDIA

Apple M4 Max 48GB

546 GB/s · Apple

Apple M4 Pro 48GB

273 GB/s · Apple

Questions people ask about an Apple M3 Max 48GB

How much VRAM does an Apple M3 Max 48GB have?

The Apple M3 Max 48GB has 48 GB of unified memory shared with the CPU, of which roughly 36 GB is available to a model once the operating system takes its share.

Can an Apple M3 Max 48GB run a 70B model?

Yes, once the macOS GPU memory limit is raised. At IQ4_XS it needs 39.99 GB and runs at around 86.1 tokens per second.

What is the best local model for an Apple M3 Max 48GB?

Gemma 4 26B A4B Instruct at Q8_0 is the strongest all-round fit: 26.69 GB used, around 34.9 tokens per second at 8k context.