Apple / unified

Apple M3

24 GB decides what fits. 100 GB/s decides how fast it runs once it does.

Computed for 24 GB, the largest configuration. The Apple M3 is also sold with 8 or 16 GB, and what fits changes with it.

Run it with 8 GB →Run it with 16 GB →

Open in the calculator →Best models for 24 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 M3 fits 214 of 320 sized models entirely in its 24 GB; the largest widely used one is Qwen3.6-35B-A3B (23.1 GB at Q4_K_M). Memory decides what fits; its 100 GB/s of bandwidth decides how fast it answers.

Largest popular model that fitsQwen3.6-35B-A3B36B params · Q4_K_M · needs 23.1 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~6.1 tok/s SlowOpen 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 M3 · 24 GB · 100 GB/s · Q4_K_M where published · 8,192 tokensSpecificationpublished dataDecode speedestimate

214 of 320 fit entirely

214 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 106 do not run at this context.

67%of the models the engine can size fit entirely

24GB of device memory

100GB/s memory bandwidth

0run with system memory

106do 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	~53 tok/s	Open →
NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters	3.46 GB	fits	~29 tok/sAbout reading pace	Open →
Qwen3-VL-8B-Instruct8.8B parameters	7.04 GB	fits	~15 tok/sAbout reading pace	Open →
Qwen3.5-9B9.7B parameters	7.05 GB	fits	~17 tok/sAbout reading pace	Open →
gemma-4-12B-it12B parameters	9.54 GB	fits	~11 tok/sAbout reading pace	Open →
gpt-oss-20b21B parameters	13.8 GB	fits	~31 tok/s	Open →
Qwen3.8-27B28B parameters	18.6 GB	fits	~6.1 tok/sSlow	Open →
Qwen3.6-27B28B parameters	18.6 GB	fits	~6.1 tok/sSlow	Open →
Kimi-Linear-48B-A3B-Instruct49B parameters	30.4 GB	short by 6.37 GB	does not run	Open →
Qwen3.8-Flash-Next180B parameters	111.6 GB	short by 87.6 GB	does not run	Open →
DeepSeek-V4-Flash-Vision-Exp305B parameters	188.1 GB	short by 164.1 GB	does not run	Open →
GLM-5.3-Flash321B parameters	198.3 GB	short by 174.3 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 M3 (24 GB) memory — 214 of 320 sized models

Every model that fitswhole model resident · offload off

Your configuration

The most demanding model that fits is Qwen2.5-VL-32B-Instruct at Q4_K_M: 23.5 GB of the 24 GB, leaving 0.52 GB spare.

Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 100 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 214 models that fit.

Model	Format	Needs	Spare	Decode	Downloads / 30d	Calculator
Qwen3.8-27BQwen · 28B params	Q4_K_M	18.6 GB	5.45 GB	~6.1 tok/sSlow	6.9M	Open →
gemma-4-26B-A4B-itGoogle · 26B params	Q4_K_M	16.8 GB	7.21 GB	~29 tok/sAbout reading pace	13M	Open →
gemma-4-31B-itGoogle · 31B params	Q4_K_M	22.2 GB	1.83 GB	~4.4 tok/sSlow	9.9M	Open →
Qwen3.5-9BQwen · 9.7B params	Q4_K_M	7.05 GB	17.0 GB	~17 tok/sAbout reading pace	9M	Open →
Qwen3.5-4BQwen · 4.7B params	Q4_K_M	3.98 GB	20.0 GB	~29 tok/sAbout reading pace	7.8M	Open →
Qwen3.6-35B-A3BQwen · 36B params	Q4_K_M	23.1 GB	0.90 GB	~39 tok/s	3.3M	Open →
gemma-4-12B-itGoogle · 12B params	Q4_K_M	9.54 GB	14.5 GB	~11 tok/sAbout reading pace	1.9M	Open →
Qwen3.6-27BQwen · 28B params	Q4_K_M	18.6 GB	5.45 GB	~6.1 tok/sSlow	2.5M	Open →
Qwen3.5-2BQwen · 2.3B params	Q4_K_M	2.32 GB	21.7 GB	~53 tok/s	4.9M	Open →
gemma-4-E4B-itGoogle · 8.0B params	Q4_K_M	5.86 GB	18.1 GB	~26 tok/sAbout reading pace	4.4M	Open →
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · 32B params	Q4_K_M	20.3 GB	3.71 GB	~4.7 tok/sSlow	530K	Open →
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params	Q4_K_M	3.46 GB	20.5 GB	~29 tok/sAbout reading pace	3.4M	Open →
gemma-4-E2B-itGoogle · 5.1B params	Q4_K_M	4.02 GB	20.0 GB	~56 tok/s	3M	Open →
Qwen3.5-0.8BQwen · 873M params	Q4_K_M	1.46 GB	22.5 GB	~86 tok/s	2.6M	Open →
Qwen3-VL-8B-InstructQwen · 8.8B params	Q4_K_M	7.04 GB	17.0 GB	~15 tok/sAbout reading pace	14.6M	Open →
Qwen3.5-27BQwen · 28B params	Q4_K_M	18.6 GB	5.45 GB	~6.1 tok/sSlow	1.9M	Open →
North-Micro-Vision-InstructCohereLabs · 2.5B params	Q4_K_M	2.99 GB	21.0 GB	~39 tok/s	180.7K	Open →
Qwen3.5-35B-A3BQwen · 36B params	Q4_K_M	23.1 GB	0.90 GB	~39 tok/s	1.6M	Open →
granite-4.2-8bIBM · 8.8B params	Q4_K_M	7.49 GB	16.5 GB	~13 tok/sAbout reading pace	128.4K	Open →
GLM-4.7-Flashzai-org · 31B params	Q4_K_M	20.4 GB	3.59 GB	~4.6 tok/sSlow	1.8M	Open →
granite-4.1-3bIBM · 3.4B params	Q4_K_M	3.72 GB	20.3 GB	~28 tok/sAbout reading pace	521.8K	Open →
LFM2.5-2.6BLiquidAI · 2.7B params	Q4_K_M	2.61 GB	21.4 GB	~41 tok/s	108.1K	Open →
Qwen3-VL-4B-InstructQwen · 4.4B params	Q4_K_M	4.72 GB	19.3 GB	~22 tok/sAbout reading pace	3.5M	Open →
granite-4.1-30bIBM · 29B params	Q4_K_M	20.4 GB	3.56 GB	~4.6 tok/sSlow	301.5K	Open →
Qwen3-VL-2B-InstructQwen · 2.1B params	Q4_K_M	3.05 GB	21.0 GB	~36 tok/s	2.8M	Open →
granite-4.2-3bIBM · 3.7B params	Q4_K_M	3.72 GB	20.3 GB	~28 tok/sAbout reading pace	50.6K	Open →
LFM2.5-230MLiquidAI · 230M params	Q4_K_M	1.05 GB	22.9 GB	~120 tok/s	88.6K	Open →
Qwen3-0.6BQwen · 752M params	Q4_K_M	2.22 GB	21.8 GB	~50 tok/s	29.7M	Open →
gpt-oss-20bOpenAI · 21B params	Q4_K_M	13.8 GB	10.2 GB	~31 tok/s	6.6M	Open →
granite-4.2-30bIBM · 29B params	Q4_K_M	20.7 GB	3.33 GB	~4.6 tok/sSlow	35.8K	Open →
granite-4.1-8bIBM · 8.8B params	Q4_K_M	7.49 GB	16.5 GB	~13 tok/sAbout reading pace	179.3K	Open →
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA · 32B params	Q4_K_M	20.3 GB	3.71 GB	~4.7 tok/sSlow	875.2K	Open →
LFM2.5-VL-3BLiquidAI · 3.1B params	Q4_K_M	2.85 GB	21.1 GB	~41 tok/s	26.7K	Open →
MiMo-V2.6-Distill-Qwen-9BNEWXiaomiMiMo · 9.4B params	Q4_K_M	6.90 GB	17.1 GB	~17 tok/sAbout reading pace	14.6K	Open →
Qwen3-4B-Instruct-2507Qwen · 4.0B params	Q4_K_M	4.72 GB	19.3 GB	~22 tok/sAbout reading pace	3.7M	Open →
Ling-3.0-tinyinclusionAI · 7.9B params	Q4_K_M	5.85 GB	18.1 GB	~67 tok/s	17.7K	Open →
Qwen3-8BQwen · 8.2B params	Q4_K_M	7.04 GB	17.0 GB	~15 tok/sAbout reading pace	10.7M	Open →
Olmo-3-7B-Instructallenai · 7.3B params	Q4_K_M	7.96 GB	16.0 GB	~13 tok/sAbout reading pace	481.7K	Open →
Qwen3-4BQwen · 4.0B params	Q4_K_M	4.51 GB	19.5 GB	~22 tok/sAbout reading pace	7.8M	Open →
LFM2.5-8B-A1BLiquidAI · 8.5B params	Q4_K_M	6.06 GB	17.9 GB	~57 tok/s	32.4K	Open →

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

Find the Apple M3: 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	24 GB
Published options	8 GB, 16 GB, 24 GB
Bandwidth	100 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

MacBook Pro (14-inch, M3, Nov 2023) - Tech Specs ↗

Retrieved 2026-09-13

Caveats

Unified memory is shared with the operating system and applications; their use is not subtracted.
Apple publishes no peak throughput figure for this chip, so no compute roof is priced for it and time to first token is withheld.

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 M3 →