Skip to content
RigCheckWhat can I run?

What can a Mac with 24 GB run locally?

What runs on a Mac with 24 GB? Every answer below is the one RigCheck's own checker for that model gives for this Mac. On a Mac the graphics and the processor share one pool of unified memory, so there is no separate RAM setting. Nothing on this page is judged separately.

For a Mac with 24 GB (24 GB of unified memory), the checkers have an answer for 8 of the 10 models, sizes and routes they cover: Qwen3.8-27B in llama.cpp, Gemma 4 31B, Gemma 4 26B-A4B, Gemma 4 12B, Gemma 4 E4B, Gemma 4 E2B once you raise the Mac's GPU wired-memory limit; Qwen3.8-Flash-Next in the Strata engine, Qwen-Image-2.1 (image generation) only with caveats (an experimental path, a planning budget or an unmeasured peak). The llama.cpp language-model answers are capacity estimates and the Nemotron 3.5, GLM-5.3-Flash and DeepSeek V4.1 Flash answers are published route matches, not measured setups; how fast a model answers depends on the chip's memory bandwidth.

Mac with 24 GB: model by model

Language models

Model (checker)On this Mac
Qwen3.8-Flash-Next in the Strata engine! Experimental path
Q2_0
No measured speed for this hardware and setup yet.
Untested: the smallest Mac Strata has measured is 32 GB. The experts would stream from the SSD, with less memory for them. Apple Silicon (M1 or newer, macOS 15 or newer) runs Strata's Metal engine, ready-made in the Mac app (.dmg). Strata calls its Mac status new: measured on three Macs, other chips untested; RigCheck counts it as experimental.
Qwen3.8-27B in llama.cpp✓ Fits (capacity estimate)
UD-IQ3_XXS · unified memory
No measured speed for this hardware and setup yet.
On a Mac, raise the GPU wired-memory limit first; the full checker gives the command.
RigCheck capacity estimate, not a measured setup.
Gemma 4 (E2B, E4B, 12B, 26B-A4B, 31B) in llama.cpp✓ Best size: fits (capacity estimate)
Gemma 4 31B: fits (capacity estimate) (UD-IQ2_XXS, unified memory); Gemma 4 26B-A4B: fits (capacity estimate) (UD-IQ3_XXS, unified memory); Gemma 4 12B: fits (capacity estimate) (Q6_K, unified memory); Gemma 4 E4B: fits (capacity estimate) (Q8_0, unified memory); Gemma 4 E2B: fits (capacity estimate) (BF16, unified memory)
No measured speed for this hardware and setup yet.
On a Mac, raise the GPU wired-memory limit first; the full checker gives the command.
RigCheck capacity estimate, not a measured setup.
No answer here: Qwen3.8-Flash-Next in llama.cpp, Mistral Medium 3.5 in llama.cpp, Mistral Large 4, Kolibri-1 (official FP8 route), Nemotron 3.5 (Bolt 74B-A9B, Super VL 120B-A12B), GLM-5.3-Flash (Unsloth GGUF), DeepSeek V4.1 Flash (September release, 1017 update) in DwarfStar
Model (checker)On this Mac
Qwen3.8-Flash-Next in llama.cpp– Not covered
Mistral Medium 3.5 in llama.cpp– Not covered
Mistral Large 4… Weights not released
smallest estimate ~210 GB vs 24 GB of memory (VRAM + RAM, or a Mac's unified memory)
Kolibri-1 (official FP8 route)– Not covered
Nemotron 3.5 (Bolt 74B-A9B, Super VL 120B-A12B)– Best size: not covered
Nemotron 3.5 Bolt 74B-A9B: not covered; Nemotron 3.5 Super VL 120B-A12B: does not fit
GLM-5.3-Flash (Unsloth GGUF)– Not covered
DeepSeek V4.1 Flash (September release, 1017 update) in DwarfStar– Not covered

Image models

Model (checker)On this Mac
Qwen-Image-2.1 (image generation)! Planning estimate only
Mac GGUF is within the planning budget; Metal execution unverified here
Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction.
No answer here: FLUX 3 Image Klein (int8, ComfyUI)
Model (checker)On this Mac
FLUX 3 Image Klein (int8, ComfyUI)– Not covered

Video models

No answer in this setup: MiniMax H3 (video + audio)
Model (checker)On this Mac
MiniMax H3 (video + audio)– Not covered

Quick setup, as in the home page finder: the Mac's 24 GB of unified memory, a 32K context and no image input for the llama.cpp capacity estimates (Nemotron 3.5, GLM-5.3-Flash and DeepSeek V4.1 Flash are matched against published recipes, memory tables and routes at their own context instead (NVIDIA's 64K / 256K recipes; Unsloth's GLM table states no context length; DwarfStar's routes per DeepSeek checkpoint (documented for the September weights, experimental for 1017), not llama.cpp).); Strata's answers on a Mac are on its experimental Apple Silicon path; for the image and video rows, Qwen-Image (a planning budget): base model, INT8, 512×512, batch one, no reference images; Kolibri-1: the official FP8 route at a 32K context; MiniMax H3: local H3-Base FL2VA recipes, assuming an NVMe drive; Nemotron 3.5: Bolt and Super VL on one card with the RAM given; FLUX 3 Image Klein: Black Forest Labs' int8 ComfyUI route on the card (on a Mac, Qwen-Image uses the base GGUF files). "With caveats" means an experimental path, an unmeasured peak, or a route the checker marks conditional. Speeds appear only where they were measured on this very machine in this setup. Pick this Mac in a checker for your exact setup.

Measured a local model on your own hardware, or tried and it failed? Send us the numbers: paste the benchmark output or log into the form (or email it). After checking it we add it to this page, labeled as a community report and shared under CC BY 4.0.

About this Mac

Any Apple Silicon Mac with 24 GB of unified memory: the checkers judge a Mac by its memory size alone. How fast a model answers depends on the chip's memory bandwidth, which differs between Macs with the same memory.

FAQ

Can a Mac with 24 GB run Qwen3.8-Flash-Next in the Strata engine?

Only on an experimental path, in RigCheck's quick setup: Q2_0; No measured speed for this hardware and setup yet; Untested: the smallest Mac Strata has measured is 32 GB. The experts would stream from the SSD, with less memory for them. Apple Silicon (M1 or newer, macOS 15 or newer) runs Strata's Metal engine, ready-made in the Mac app (.dmg). Strata calls its Mac status new: measured on three Macs, other chips untested; RigCheck counts it as experimental. The full checker takes your exact setup (RAM, disk, operating system, processor) and gives the install steps.

Can a Mac with 24 GB run Qwen3.8-27B in llama.cpp?

Yes, by RigCheck's capacity estimate, in RigCheck's quick setup: UD-IQ3_XXS · unified memory; No measured speed for this hardware and setup yet; On a Mac, raise the GPU wired-memory limit first; the full checker gives the command; RigCheck capacity estimate, not a measured setup. The full checker takes your exact setup (context length, RAM, image input) and gives the command to start it.

Can a Mac with 24 GB run Gemma 4 (E2B, E4B, 12B, 26B-A4B, 31B) in llama.cpp?

Yes, by RigCheck's capacity estimate, in RigCheck's quick setup: Gemma 4 31B: fits (capacity estimate) (UD-IQ2_XXS, unified memory); Gemma 4 26B-A4B: fits (capacity estimate) (UD-IQ3_XXS, unified memory); Gemma 4 12B: fits (capacity estimate) (Q6_K, unified memory); Gemma 4 E4B: fits (capacity estimate) (Q8_0, unified memory); Gemma 4 E2B: fits (capacity estimate) (BF16, unified memory); No measured speed for this hardware and setup yet; On a Mac, raise the GPU wired-memory limit first; the full checker gives the command; RigCheck capacity estimate, not a measured setup. The full checker takes your exact setup (context length, RAM, image input) and gives the command to start it.

Can a Mac with 24 GB run Qwen-Image-2.1 (image generation)?

Only as a planning estimate: the checker's uncalibrated memory budget, offload peak unverified, in RigCheck's quick setup: Mac GGUF is within the planning budget; Metal execution unverified here; Uncalibrated allowances, not a minimum or a guarantee. Full checkpoint files are counted in host RAM even when mmap or sequential loading can use less. Actual peak depends on attention, prefix caches, VAE tiling, reference sizes and backend. No speed prediction. The full checker lets you change the task, resolution, references and offload (batch is fixed at one), and lists the files.

Other Macs

Mac with 32 GB · Mac with 48 GB · Mac with 64 GB · Mac with 96 GB · Mac with M5 Max (128 GB) · Mac Studio M3 Ultra (256 GB) · All Macs · Graphics cards

Sources