Apple / unified

Apple M5 Max

128 GB decides what fits. 614 GB/s decides how fast it runs once it does.

Computed for 128 GB, the largest configuration. The Apple M5 Max is also sold with 36, 48 or 64 GB, and what fits changes with it; some configurations also have less bandwidth, listed below.

Run it with 36 GB (460 GB/s) →Run it with 48 GB (614 GB/s) →Run it with 64 GB (614 GB/s) →

Open in the calculator →Best models for 128 GB, on every card that size →

Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.

Quick answer

The Apple M5 Max fits 248 of 320 sized models entirely in its 128 GB; the largest widely used one is Qwen3.8-Flash-Next (111.6 GB at Q4_K_M). Memory decides what fits; its 614 GB/s of bandwidth decides how fast it answers.

Largest popular model that fitsQwen3.8-Flash-Next180B params · Q4_K_M · needs 111.6 GB~84 tok/s Faster than you readOpen in the calculator →
Best fast pickStep-3.5-Flash199B params · Q4_K_M · needs 127.0 GB~39 tok/s Faster than you readOpen in the calculator →
Most downloaded that fitsQwen3.8-27B28B params · Q4_K_M · needs 18.6 GB~32 tok/s Faster than you readOpen in the calculator →

At 8,192 tokens of context with the whole model in device memory. Speeds are estimates from memory bandwidth, not benchmarks run on this card.

Apple M5 Max · 128 GB · 614 GB/s · Q4_K_M where published · 8,192 tokensSpecificationpublished dataDecode speedestimate

248 of 320 fit entirely

248 of the 320 models the engine can size fit entirely in device memory at Q4_K_M where it is published, otherwise the nearest published format, and 8,192 tokens. Unified memory is one pool, so there is no second memory tier to spill into; the remaining 72 do not run at this context.

78%of the models the engine can size fit entirely

128GB of device memory

614GB/s memory bandwidth

0run with system memory

72do not run at 8,192 tokens

Featured models · Q4_K_M at 8,192 tokens, including offload

Model	Needs	Verdict	Decode	Calculator
Qwen3.5-2B2.3B parameters	2.32 GB	fits	~128 tok/s	Open →
NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters	3.46 GB	fits	~97 tok/s	Open →
Qwen3-VL-8B-Instruct8.8B parameters	7.04 GB	fits	~63 tok/s	Open →
Qwen3.5-9B9.7B parameters	7.05 GB	fits	~71 tok/s	Open →
gemma-4-12B-it12B parameters	9.54 GB	fits	~50 tok/s	Open →
gpt-oss-20b21B parameters	13.8 GB	fits	~100 tok/s	Open →
Qwen3.8-27B28B parameters	18.6 GB	fits	~32 tok/s	Open →
Qwen3.6-27B28B parameters	18.6 GB	fits	~32 tok/s	Open →
Kimi-Linear-48B-A3B-Instruct49B parameters	30.4 GB	fits	~112 tok/s	Open →
Qwen3.8-Flash-Next180B parameters	111.6 GB	fits	~84 tok/s	Open →
DeepSeek-V4-Flash-Vision-Exp305B parameters	188.1 GB	short by 60.1 GB	does not run	Open →
GLM-5.3-Flash321B parameters	198.3 GB	short by 70.3 GB	does not run	Open →

These examples are selected from prominent labs using the catalogue’s latest Hugging Face 30-day downloads and repository-creation freshness signal, with newer releases guaranteed a place. Offloaded rows assume 32 GB of system RAM, and a speed is only shown for a row that runs. Fitting in memory is not the same as loading: whether the runtime and version you have supports each architecture and format on this machine has not been tested here. Each “Open” link carries the same model, format, context and RAM into the calculator.

Fits entirely in Apple M5 Max (M5 Max 18-core CPU / 40-core GPU, 128 GB) memory — 248 of 320 sized models

Every model that fitswhole model resident · offload off

Your configuration

The most demanding model that fits is Step-3.5-Flash at Q4_K_M: 127.0 GB of the 128 GB, leaving 1.03 GB spare.

Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 614 GB/s. Each row is a run of the engine for this configuration; the rows start with current, prominent releases and “fits” is memory, not a tested runtime. Older or less prominent models remain available through this search and “Show all”.

Find a model in this list

Showing 40 of 248 models that fit.

Model	Format	Needs	Spare	Decode	Downloads / 30d	Calculator
Qwen3.8-27BQwen · 28B params	Q4_K_M	18.6 GB	109.4 GB	~32 tok/s	6.9M	Open →
Qwen3.8-Flash-NextNEWQwen · 180B params	Q4_K_M	111.6 GB	16.4 GB	~84 tok/s	1.4M	Open →
gemma-4-26B-A4B-itGoogle · 26B params	Q4_K_M	16.8 GB	111.2 GB	~97 tok/s	13M	Open →
gemma-4-31B-itGoogle · 31B params	Q4_K_M	22.2 GB	105.8 GB	~24 tok/sAbout reading pace	9.9M	Open →
Qwen3.5-9BQwen · 9.7B params	Q4_K_M	7.05 GB	121.0 GB	~71 tok/s	9M	Open →
Qwen3.5-4BQwen · 4.7B params	Q4_K_M	3.98 GB	124.0 GB	~96 tok/s	7.8M	Open →
Qwen3.6-35B-A3BQwen · 36B params	Q4_K_M	23.1 GB	104.9 GB	~112 tok/s	3.3M	Open →
gemma-4-12B-itGoogle · 12B params	Q4_K_M	9.54 GB	118.5 GB	~50 tok/s	1.9M	Open →
Qwen3.6-27BQwen · 28B params	Q4_K_M	18.6 GB	109.4 GB	~32 tok/s	2.5M	Open →
Qwen3.5-2BQwen · 2.3B params	Q4_K_M	2.32 GB	125.7 GB	~128 tok/s	4.9M	Open →
gemma-4-E4B-itGoogle · 8.0B params	Q4_K_M	5.86 GB	122.1 GB	~91 tok/s	4.4M	Open →
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · 32B params	Q4_K_M	20.3 GB	107.7 GB	~25 tok/sAbout reading pace	530K	Open →
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params	Q4_K_M	3.46 GB	124.5 GB	~97 tok/s	3.4M	Open →
gemma-4-E2B-itGoogle · 5.1B params	Q4_K_M	4.02 GB	124.0 GB	~130 tok/s	3M	Open →
Qwen3.5-0.8BQwen · 873M params	Q4_K_M	1.46 GB	126.5 GB	~150 tok/s	2.6M	Open →
Qwen3-VL-8B-InstructQwen · 8.8B params	Q4_K_M	7.04 GB	121.0 GB	~63 tok/s	14.6M	Open →
Qwen3.5-27BQwen · 28B params	Q4_K_M	18.6 GB	109.4 GB	~32 tok/s	1.9M	Open →
North-Micro-Vision-InstructCohereLabs · 2.5B params	Q4_K_M	2.99 GB	125.0 GB	~112 tok/s	180.7K	Open →
Qwen3.5-35B-A3BQwen · 36B params	Q4_K_M	23.1 GB	104.9 GB	~112 tok/s	1.6M	Open →
NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA · 124B params	Q4_K_M	76.9 GB	51.1 GB	~7.2 tok/sSlow	1.2M	Open →
granite-4.2-8bIBM · 8.8B params	Q4_K_M	7.49 GB	120.5 GB	~59 tok/s	128.4K	Open →
GLM-4.7-Flashzai-org · 31B params	Q4_K_M	20.4 GB	107.6 GB	~25 tok/sAbout reading pace	1.8M	Open →
granite-4.1-3bIBM · 3.4B params	Q4_K_M	3.72 GB	124.3 GB	~95 tok/s	521.8K	Open →
LFM2.5-2.6BLiquidAI · 2.7B params	Q4_K_M	2.61 GB	125.4 GB	~115 tok/s	108.1K	Open →
Qwen3-VL-4B-InstructQwen · 4.4B params	Q4_K_M	4.72 GB	123.3 GB	~82 tok/s	3.5M	Open →
granite-4.1-30bIBM · 29B params	Q4_K_M	20.4 GB	107.6 GB	~25 tok/sAbout reading pace	301.5K	Open →
Qwen3.5-122B-A10BQwen · 125B params	Q4_K_M	77.9 GB	50.1 GB	~69 tok/s	512.6K	Open →
Qwen3-VL-2B-InstructQwen · 2.1B params	Q4_K_M	3.05 GB	125.0 GB	~108 tok/s	2.8M	Open →
granite-4.2-3bIBM · 3.7B params	Q4_K_M	3.72 GB	124.3 GB	~95 tok/s	50.6K	Open →
LFM2.5-230MLiquidAI · 230M params	Q4_K_M	1.05 GB	126.9 GB	~163 tok/s	88.6K	Open →
Qwen3-0.6BQwen · 752M params	Q4_K_M	2.22 GB	125.8 GB	~125 tok/s	29.7M	Open →
Qwen3-Coder-NextQwen · 80B params	Q4_K_M	50.0 GB	78.0 GB	~95 tok/s	596.3K	Open →
gpt-oss-20bOpenAI · 21B params	Q4_K_M	13.8 GB	114.2 GB	~100 tok/s	6.6M	Open →
granite-4.2-30bIBM · 29B params	Q4_K_M	20.7 GB	107.3 GB	~25 tok/sAbout reading pace	35.8K	Open →
granite-4.1-8bIBM · 8.8B params	Q4_K_M	7.49 GB	120.5 GB	~59 tok/s	179.3K	Open →
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA · 32B params	Q4_K_M	20.3 GB	107.7 GB	~25 tok/sAbout reading pace	875.2K	Open →
gpt-oss-120bOpenAI · 117B params	Q4_K_M	71.9 GB	56.1 GB	~84 tok/s	4.5M	Open →
LFM2.5-VL-3BLiquidAI · 3.1B params	Q4_K_M	2.85 GB	125.1 GB	~115 tok/s	26.7K	Open →
MiMo-V2.6-Distill-Qwen-9BNEWXiaomiMiMo · 9.4B params	Q4_K_M	6.90 GB	121.1 GB	~71 tok/s	14.6K	Open →
Qwen3-4B-Instruct-2507Qwen · 4.0B params	Q4_K_M	4.72 GB	123.3 GB	~82 tok/s	3.7M	Open →

Sized at the format most people actually download, not at FP16. The catalogue ordered by downloads →

Find the Apple M5 Max: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.

Under the hood

The specification behind every figure

What the manufacturer publishes for this device, and the pages it was read from.

Manufacturer specification

Memory scope	unified-system
Capacity	128 GB
Published options	36 GB, 48 GB, 64 GB, 128 GB
Bandwidth	614 GB/s
Memory type	unified memory
Bus width	Not published
FP32 peak	Not published
Dense matrix peak	Not published without sparsity
Power	Not published

Source ledger

Mac Studio - Technical Specifications ↗

Retrieved 2026-08-30

Caveats

The flat bandwidth/capacity fields are maxima; configurations preserve Apple's exact CPU/GPU and bandwidth/capacity groupings. No VRAM capacity is claimed.

Official configurations

Configuration	GPU cores	Memory	Bandwidth
M5 Max 18-core CPU / 32-core GPU	32	36 GB	460 GB/s
M5 Max 18-core CPU / 40-core GPU	40	48 / 64 / 128 GB	614 GB/s

Published capacity is a hardware ceiling, not guaranteed free runtime memory. The calculator shows the runtime reserve separately rather than folding it into a single number.

Run the diagnostic on the Apple M5 Max →