Skip to content
Local AI Wizard
Your machine
Theme

MacBook Pro 16-inch · M5 Max · 18-core CPU / 40-core GPU · 48 GB unified

Apple · MacBook Pro 16-inch · 2026

160 text models run well · 614 GB/s bandwidth

Models on this hardware

Start here

Text

Within 44 GB: 160 run well · 1 tight · 37 reviewed

Text · LiveBench · overall

0–100 · higher is better

  • Color = publisher

Source: LiveBench 2026-06-25 · collected 2026-09-26 · Open models without a score are not drawn (no score ≠ 0).

Rows run well first, then tight fits; within each, reviewed models, then Hub downloads over 30 days, not quality. Sort a score column to rank by that source alone. No model in the catalog needs between 44 GB and the 48 GB installed, so none runs only partly on the GPU. No other text model would run well with 64 GB.
Text models that run well within 44 GB
Smaug MiniAbacus AI · 27BQ4 · published params · source76.9Not on the LMArena text leaderboard of 2026-10-22~29 GBQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · LMArena 1,437Q4 · published params · source75.31,437 ± 5~29 GBQ4 · published paramssource
Qwen3.6 27BAlibaba · 27BQ4 · published params · source64.0Not on the LMArena text leaderboard of 2026-10-22~29 GBQ4 · published paramssource
Qwen3 14BAlibaba · 14.8BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~20 GBQ4 · published paramssource
Gemma 4 31BGoogle · 30.7B · LMArena 1,452Q4 · published params · sourceNo comparable published result1,452 ± 7~32 GBQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · LMArena 1,437Q4 · published params · sourceNo comparable published result1,437 ± 7~27 GBQ4 · published paramssource
Qwen3 8BAlibaba · 8.2BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~15 GBQ4 · published paramssource
Qwen3.5 9BAlibaba · 9BQ4 · published params · sourceNo comparable published resultNot on the LMArena text leaderboard of 2026-10-22~15 GBQ4 · published paramssource
8 of 161

LMArena ratings in this table: LMArena 2026-10-22 · collected 2026-10-25 · dataset · CC BY 4.0

Tight fit: it runs, but leaves less than 4.4 GB free beyond the 8 GB the system keeps (the memory figure already includes that reserve).

Every reviewed text model here 37

Every one that runs here, well or slowly, scored or not; 19 of 37 have a LiveBench or LMArena result. Run well first, then tight fits, then slow; within each, by Hub downloads over 30 days, read 2026-10-25, not by quality.

Reviewed text models that run on MacBook Pro 16-inch · M5 Max · 18-core CPU / 40-core GPU · 48 GB unified
Qwen3 14BAlibaba · 14.8BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~20 GB9.0Apache 2.010.4M
Gemma 4 31BGoogle · 30.7BNot in LiveBench 2026-06-251,452~32 GB18.3Apache 2.08.4M
Gemma 4 26B A4BGoogle · 25.2BNot in LiveBench 2026-06-251,437~27 GB16.9Apache 2.08.2M
Qwen3 8BAlibaba · 8.2BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~15 GB5.0Apache 2.08.1M
Qwen3.8 27BAlibaba · 27B75.31,437~29 GB16.5Apache 2.07.8M
Qwen3.5 9BAlibaba · 9BNot in LiveBench 2026-06-25Not on the LMArena text leaderboard of 2026-10-22~15 GB5.7Apache 2.06.1M
gpt-oss-20bOpenAI · 21BNot in LiveBench 2026-06-251,317~24 GB11.6Apache 2.05.8M
Llama 3.1 8B InstructMeta · 8BNot in LiveBench 2026-06-251,211~14 GB4.9Llama 3.14.8M
8 of 37

Browse Text models

Adjust the estimate: quantization, context, reserveloads the live catalog

Vision

Within 44 GB: 142 run well · 10 reviewed

Vision · LMArena

rating · higher is better

  • Color = publisher

Source: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0 · Models without a rating are left out, not scored as zero.

Rows run well first, then tight fits; within each, reviewed models, then Hub downloads over 30 days, not quality. Sort a score column to rank by that source alone. No model in the catalog needs between 44 GB and the 48 GB installed, so none runs only partly on the GPU. No other vision model would run well with 64 GB.
Vision models that run well within 44 GB
Gemma 4 31BGoogle · 30.7B · Image to text · LMArena 1,262Q4 · published params · source1,262 ± 6~32 GBQ4 · published paramssource
Qwen3.8 27BAlibaba · 27B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 8~29 GBQ4 · published paramssource
Gemma 4 26B A4BGoogle · 25.2B · Image to text · LMArena 1,242Q4 · published params · source1,242 ± 6~27 GBQ4 · published paramssource
gemma-3-27b-itgoogle · 27.43B · Image to text · LMArena 1,160Q4 · Hugging Face count · source1,160 ± 8~29 GBQ4 · Hugging Face countsource
Qwen2.5-VL-32B-InstructQwen · 33.45B · Image to text · LMArena 1,119Q4 · Hugging Face count · source1,119 ± 15~34 GBQ4 · Hugging Face countsource
Molmo2-8Ballenai · 8.7B · Image to text · LMArena 1,112Q4 · Hugging Face count · source1,112 ± 20~15 GBQ4 · Hugging Face countsource
Qwen2-VL-7B-InstructQwen · 8.29B · Image to text · LMArena 1,031Q4 · Hugging Face count · source1,031 ± 11~15 GBQ4 · Hugging Face countsource
Molmo-7B-D-0924allenai · 8B · Image to text · LMArena 994Q4 · Hugging Face count · source994 ± 14~14 GBQ4 · Hugging Face countsource
8 of 142

LMArena ratings in this table: LMArena 2026-10-19 · collected 2026-10-25 · dataset · CC BY 4.0

12 more vision models in the catalog have no usable memory figure or parameter count for this profile. Browse Vision models

Image

69 within 44 GB · 5 more with 64 GB

Image · Prompt alignment · GenEval

0–1 · higher is better

Source: GenEval · 2023 · reviewed 2026-10-05 · Published quality in the original benchmark preset; not measured on this hardware.

Image models within 44 GB
Stable Diffusion XL 1.0Stability AI · 2.6B · Text to imagePlatform path documented · Apple Core ML · source0.55Not on the LMArena text-to-image leaderboard of 2026-10-07Documented path without a memory figurePlatform path documentedApple Core ML · source
Stable Diffusion 1.5Stability AI · 0.98B · Text to imagePlatform path documented · Apple Core ML · source0.43Not on the LMArena text-to-image leaderboard of 2026-10-07Documented path without a memory figurePlatform path documentedApple Core ML · source
HiDream-I1-FullHiDream-ai · 17.1B · Text to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~44 GB16-bit est. · paramssource
HiDream-I1-DevHiDream · 17B · Text to image16-bit est. · params · sourceNo comparable published resultNot on the LMArena text-to-image leaderboard of 2026-10-07~43 GB16-bit est. · paramssource
HiDream-I1-FastHiDream · 17B · Text to image16-bit est. · params · sourceNo comparable published resultNot on the LMArena text-to-image leaderboard of 2026-10-07~43 GB16-bit est. · paramssource
HunyuanImage-2.1Tencent Hunyuan · 17B · Text to image16-bit est. · params · sourceNo comparable published resultNot on the LMArena text-to-image leaderboard of 2026-10-07~43 GB16-bit est. · paramssource
JoyAI-Image-Edit-Diffusersjdopensource · 16.3B · Image to image16-bit est. · params · sourceNo comparable published resultNot reviewed for LMArena~42 GB16-bit est. · paramssource
GLM-ImageZ AI · 16B · Text to image · LMArena 1,01216-bit est. · sum of parts · sourceNo comparable published result1,012 ± 9~41 GB16-bit est. · sum of partssource
8 of 69

LMArena ratings in this table: LMArena 2026-10-07 · collected 2026-10-25 · dataset · CC BY 4.0

With 64 GB you also run… 5

The next memory size on this ladder. Figures are the requirement on this hardware type.

17 more image models in the catalog have no usable memory figure or parameter count for this profile. Browse Image models

Video

55 within 44 GB · 11 more with 64 GB
Video models within 44 GB
Wan2.1-VACE-14BWan-AI · 17.3B · Image to video16-bit est. · params · source~44 GB16-bit est. · paramssource
Wan2.1-VACE-14B-diffusersWan-AI · 17.3B · Image to video16-bit est. · params · source~44 GB16-bit est. · paramssource
Wan2.2-Animate-14BWan-AI · 17.3B · Video to video16-bit est. · params · source~44 GB16-bit est. · paramssource
ATIbytedance-research · 16.4B · Image to video16-bit est. · params · source~42 GB16-bit est. · paramssource
Wan2.1-I2V-14B-480PWan-AI · 16.4B · Image to video16-bit est. · params · source~42 GB16-bit est. · paramssource
Wan2.1-I2V-14B-480P-DiffusersWan-AI · 16.4B · Image to video16-bit est. · params · source~42 GB16-bit est. · paramssource
Wan2.1-I2V-14B-720PWan-AI · 16.4B · Image to video16-bit est. · params · source~42 GB16-bit est. · paramssource
Wan2.1-I2V-14B-720P-DiffusersWan-AI · 16.4B · Image to video16-bit est. · params · source~42 GB16-bit est. · paramssource
8 of 55

How this list works Documented execution paths on this hardware first, then publisher minimums (CUDA or Apple MPS).

With 64 GB you also run… 11

The next memory size on this ladder. Figures are the requirement on this hardware type.

6 of 11

21 more video models in the catalog have no usable memory figure or parameter count for this profile. Browse Video models

Audio

130 within 44 GB

Audio · Word error rate · Open ASR

% · lower is better

Source: Word error rate · Open ASR · reviewed 2026-10-20 · Published quality in the original benchmark preset; not measured on this hardware.

Audio models within 44 GB
Whisper large-v3-turboOpenAI · 0.81B · Speech to textPlatform path documented · whisper.cpp / Metal · source7.83Documented path without a memory figurePlatform path documentedwhisper.cpp / Metal · source
Whisper large-v3OpenAI · 1.55B · Speech to textPlatform path documented · whisper.cpp / Metal · source7.44Documented path without a memory figurePlatform path documentedwhisper.cpp / Metal · source
Kimi-Audio-7Bmoonshotai · 9.8B · Text to speech16-bit est. · params · sourceNo comparable published result~26 GB16-bit est. · paramssource
Kimi-Audio-7B-Instructmoonshotai · 9.8B · Text to speech16-bit est. · params · sourceNo comparable published result~26 GB16-bit est. · paramssource
Llasa-8BHKUSTAudio · 8.6B · Text to speech16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
MOSS-TTS-v1.5OpenMOSS-Team · 8.5B · Text to speech16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
personaplex-7b-v1nvidia · 8.4B · Speech to speech / audio to audio16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
Qwen2-Audio-7B-InstructQwen · 8.4B · Speech to text16-bit est. · params · sourceNo comparable published result~23 GB16-bit est. · paramssource
8 of 130

35 more audio models in the catalog have no usable memory figure or parameter count for this profile. Browse Audio models

Embeddings

91 run well within 44 GB

Embeddings · MTEB (Multilingual, v2) · mean(task)

0–100 · higher is better

  • Color = publisher

Source: MTEB results (curated rows, sourced per model)

Embeddings models that run well within 44 GB
Qwen3-Embedding 8BAlibaba (Qwen)8-bit · published params · source70.6~12 GB8-bit · published paramssource
Qwen3-Embedding 4BAlibaba (Qwen)8-bit · published params · source69.5~7 GB8-bit · published paramssource
Harrier OSS v1 (0.6B)Microsoft8-bit · published params · source69.0~3 GB8-bit · published paramssource
Qwen3-Embedding 0.6BAlibaba (Qwen)8-bit · published params · source64.3~3 GB8-bit · published paramssource
Multilingual E5 Large Instructintfloat8-bit · published params · source63.2~3 GB8-bit · published paramssource
EmbeddingGemma 2Google8-bit · published params · source61.4~3 GB8-bit · published paramssource
EmbeddingGemma (300M)Google8-bit · published params · source61.1~3 GB8-bit · published paramssource
BGE-M3BAAI8-bit · published params · source59.6~3 GB8-bit · published paramssource
8 of 91

Browse Embeddings models

Runs well within 44 GB of unified memory · planning estimates, not measured speed bundled catalog copy · 1,777 repositories · checked

Measurements

Published tokens per second, exactly as measured; never estimated.

Published measurements on this hardware
Llama 7B Q4_0 (llama-bench reference model)Not named by the summary table; llama-bench…Apple M5 Max · 40-core GPU · 614 GB/s (memory size not stated by the source)119.92Q4_0
0 / 128 · Single llama-bench process;…
Metal
llama.cpp commit c1d0e7a
llama.cpp Apple Silicon summary · community result
2026-10-25

Specifications

29 sourced fields; the source is named once per group, and a field from another source links to it. Official specifications

Unified memory48 GBShared by CPU and GPU · source
Memory bandwidth614 GB/sManufacturer spec · not model speed · source
Official list price (MSRP)USD 4,999.00US · manufacturer store, read · source · not a tracked offer
Where to buyApple StoreManufacturer link · this configuration · US · recorded

Marker: the best LiveBench-scored text model that runs well here. No other text model would run well with 64 GB. Q4 planning estimate, not a measured fit.

Reviewed · Manufacturer source

CPU cores
18
Processor
Apple M5 Max
GPU cores
40
Graphics processor
Apple M5 Max GPU
GPU runtime status
Not stated by the source
Memory capacity
48 GB
Memory kind
Unified memory
Memory bandwidth
614 GB/s
Battery capacity
100 Wh
Bluetooth
Bluetooth 6
CPU performance cores
12
CPU super cores
6
Dimensions (cm)
35.57 × 24.81 × 1.68 (W × D × H)
Display size
16.2 in
Peak display brightness
1,600 nits
Display refresh rate
120 Hz
Display resolution
3456 × 2234
Sustained display brightness
1,000 nits
Maximum external displays
4
Included power adapter
140 W
Neural Engine cores
16
Operating system
macOS
Ports
3 × Thunderbolt 5 (USB-C) · HDMI · SDXC · MagSafe 3 · 3.5 mm headphone jack
Release date
2026-03-11
Storage options
Base storage: 2 TB; configure-to-order options: 4 TB or 8 TB.
Maximum Thunderbolt rate
120 Gb/s
Weight
2.15 kg
Wi-Fi
Wi-Fi 7 (802.11be)
Introduced
2026

Apple M5 Max · Apple M5 Max GPU with 48 GB unified memory. Runtime support and local inference speed are not verified.

Photo: Apple family photo · memory configuration is not pictured. · Manufacturer source

Memory bandwidth is not measured model speed; verify runtime and checkpoint compatibility. Hardware specification reviewed: 2026-10-13.

How estimates work
Candidates
Reviewed pages use published parameter counts; automatic text candidates use official repository tensor counts (packed quantized weights and unsupported architectures excluded).
Planning
Q4 weights + 20% allowance + reserve: 25% of unified or system memory (at least 2 GB, at most 8 GB; 8 GB here) or 2 GB per dedicated GPU. Adjustable in “Adjust the estimate”. No KV cache is calculated from context.
Fit tiers
Runs well: the estimate fits the fast memory (VRAM, or unified memory within the macOS GPU share). Runs slowly: within the machine's memory but outside the fast part; a graphics card offloads layers to PC RAM (the listed RAM, or 32 GB assumed). Doesn't run: above both. Tiers are planning estimates, never a speed.
Vision
Vision-language models use the Q4 planning estimate from the parameter count (published by the model page, or read from Hugging Face). Classic vision models (classify, detect, segment) use a 16-bit estimate. No vision benchmark is tracked, so rows carry no score.
Media and embeddings
Media rows use documented execution paths (exact hardware or platform) and publisher minimums; a published requirement above this memory moves a model to the next tier. Without either, a 16-bit estimate from the published parameter count (× 1.2 + 2 GB), labelled as such. Embeddings use 8-bit weights + 20% + 2 GB.

Local AI basics: parameters, Q4 and memory · Full model catalog · Data and methodology

Alternatives

Other machines on the same memory ladder (unified memory); each page lists the models that fit it.