99↗tokens.

MacBook Pro M5 Pro · 48 GB (16-core GPU)

MacBook Pro, Apple M5 Pro, 15-core CPU / 16-core GPU / 48 GB unified memory

Physical memory48GiB
Available in calculator 36.0GiB
Peak bandwidth 307GB/s
Use in calculator

Use Metal or MLX with support for the chosen model. The OS and other apps share memory; Metal working-set limits vary.

Specifications and setup

Memory
48 GiB Unified memory
Connection
On-chip unified memory; no discrete VRAM pool
Runtime
Metal / MLX. Actual usable memory is runtime- and OS-dependent; query recommendedMaxWorkingSetSize rather than treating all RAM as VRAM.
Bandwidth basis
Apple-published chip bandwidth; shared CPU/GPU traffic reduces bandwidth available to inference.
System reserve
Planner assumption: 25% of installed memory reserved for macOS, other apps and allocation headroom. This is adjustable, not an Apple GPU-allocation guarantee.

Model fit at Q4 and 8K

One request, FP16 conversation cache, default reserves. “Not verified” means the model’s cache formula needs more research.

ModelMemory neededAvailableEstimateOpen plan
Qwen3.5 0.8B0.9B · Dense1.6 GiB36.0 GiBRoom to spare
Qwen3.5 2B2.3B · Dense2.4 GiB36.0 GiBRoom to spare
SmolLM3 3B3.1B · Dense3.3 GiB36.0 GiBRoom to spare
Granite 4.2 3B3.7B · Dense3.7 GiB36.0 GiBRoom to spare
Ministral 3 3B3.8B · Dense4.0 GiB36.0 GiBRoom to spare
Qwen3.5 4B4.7B · Dense3.9 GiB36.0 GiBRoom to spare
Gemma 4 E2B5.1B · Dense3.9 GiB36.0 GiBConditional · Room to spare
OLMo 3 7B Instruct7.3B · Dense7.6 GiB36.0 GiBConditional · Room to spare
Gemma 4 E4B8.0B · Dense5.6 GiB36.0 GiBConditional · Room to spare
Granite 4.2 8B8.8B · Dense7.2 GiB36.0 GiBRoom to spare
Nemotron Nano 9B v28.9B · Dense6.2 GiB36.0 GiBRoom to spare
Ministral 3 8B8.9B · Dense7.0 GiB36.0 GiBRoom to spare
Qwen3.5 9B9.7B · Dense6.7 GiB36.0 GiBRoom to spare
GLM-4.6V Flash 9B10.3B · Dense7.1 GiB36.0 GiBRoom to spare
Gemma 4 12B12.0B · Dense8.1 GiB36.0 GiBConditional · Room to spare
Ministral 3 14B13.9B · Dense10.0 GiB36.0 GiBRoom to spare
Phi-4 Reasoning Plus 14B14.7B · Dense10.8 GiB36.0 GiBRoom to spare
gpt-oss 20B20.9B · Mixture of experts12.9 GiB36.0 GiBConditional · Room to spare
ERNIE 4.5 21B-A3B Thinking21.8B · Mixture of experts13.6 GiB36.0 GiBRoom to spare
Devstral Small 2 24B24.0B · Dense15.7 GiB36.0 GiBRoom to spare
Gemma 4 26B-A4B25.8B · Mixture of experts15.9 GiB36.0 GiBConditional · Room to spare
Qwen3.8 27B27.8B · Dense17.4 GiB36.0 GiBRoom to spare
Granite 4.2 30B29.3B · Dense19.7 GiB36.0 GiBRoom to spare
Qwen3 Coder 30B-A3B30.5B · Mixture of experts19.2 GiB36.0 GiBRoom to spare
GLM-4.7 Flash 30B-A3B31.2B · Mixture of experts19.3 GiB36.0 GiBConditional · Room to spare
Gemma 4 31B31.3B · Dense20.3 GiB36.0 GiBConditional · Room to spare
Nemotron 3 Nano 30B-A3B31.6B · Mixture of experts19.2 GiB36.0 GiBRoom to spare
OLMo 3.1 32B Think32.2B · Dense20.7 GiB36.0 GiBConditional · Room to spare
Qwen3.6 35B-A3B36.0B · Mixture of experts21.9 GiB36.0 GiBRoom to spare
Kimi Linear 48B-A3B49.1B · Mixture of experts30.8 GiB36.0 GiBConditional · Room to spare
Llama 3.3 70B70.6B · Dense45.1 GiB36.0 GiBOver capacity
Qwen3 Coder Next 80B-A3B79.7B · Mixture of experts48.3 GiB36.0 GiBOver capacity
Llama 4 Scout 109B-A17B108.6B · Mixture of experts67.1 GiB36.0 GiBConditional · Over capacity
gpt-oss 120B116.8B · Mixture of experts70.8 GiB36.0 GiBConditional · Over capacity
Mistral Small 4 119B-A6.5B119.4B · Mixture of experts72.2 GiB36.0 GiBConditional · Over capacity
Nemotron 3 Super 120B-A12B123.6B · Mixture of experts74.8 GiB36.0 GiBOver capacity
Devstral 2 123B125.0B · Dense78.2 GiB36.0 GiBOver capacity
Qwen3.5 122B-A10B125.1B · Mixture of experts75.8 GiB36.0 GiBOver capacity
Mistral Medium 3.5 128B127.7B · Dense79.8 GiB36.0 GiBOver capacity
Qwen3.8 Flash Next180.0B · Mixture of experts181.0 GiB36.0 GiBConditional · Over capacity
MiniMax M2.7228.7B · Mixture of experts140.0 GiB36.0 GiBOver capacity
DeepSeek V4 Flash 0731304.2B · Mixture of experts183.6 GiB36.0 GiBConditional · Over capacity
DeepSeek V4 Flash Vision304.6B · Mixture of experts183.9 GiB36.0 GiBConditional · Over capacity
GLM-5.3 Flash321.3B · Mixture of experts194.1 GiB36.0 GiBConditional · Over capacity
Qwen3.5 397B-A17B403.4B · Mixture of experts243.9 GiB36.0 GiBOver capacity
MiniMax M3427.0B · Mixture of experts258.8 GiB36.0 GiBConditional · Over capacity
Nemotron 3 Ultra 550B-A55B560.5B · Mixture of experts338.8 GiB36.0 GiBOver capacity
Mistral Large 3 675B-A41B675.0B · Mixture of experts407.9 GiB36.0 GiBConditional · Over capacity
GLM-5.3753.3B · Mixture of experts455.3 GiB36.0 GiBConditional · Over capacity
Kimi K2.7 Code1,026.9B · Mixture of experts620.3 GiB36.0 GiBConditional · Over capacity
DeepSeek V4 Pro 08131,650.5B · Mixture of experts996.2 GiB36.0 GiBConditional · Over capacity
Qwen3.8 2.4T-A95B2,446.2B · Mixture of experts1,477.5 GiB36.0 GiBOver capacity
Kimi K32,779.9B · Mixture of experts1,678.3 GiB36.0 GiBConditional · Over capacity