Locara
Mac compatibility

Will Locara run on your Mac?
Pick a chip. See what fits.

Locara is Apple-Silicon-only. Every model and every app has a memory floor that depends on the chip, the bandwidth, and the RAM tier you bought. The tables below are computed at build time from each app's locara.json manifest and a curated registry of every M-series Mac since 2020 — no guessing, no marketing numbers.

How the numbers are computed

One formula. Three inputs. Reproducible from the manifest.

For every app, we add up the resident memory cost of all its pinned models, plus a 1 GB activation + KV-cache overhead, and compare against 70% of the Mac's RAM — leaving 30% for macOS and the user's other apps. The author-declared profiles.mid.min_ram_gb becomes a hard floor. Mac variants and bandwidth come from the curated lineup table.

  • Model size  params × bpw / 8 — Q4_K_M ≈ 4.89 bpw. Derivation
  • Fit rule  working_set ≤ 0.7 × ram_gb.
  • Bandwidth   sets tok/s, not fit. See per-SKU table
Macs

Every M-series Mac — RAM, bandwidth, fit.

Bandwidth determines decode speed (tok/s); RAM determines what fits. The "largest fit" column shows the biggest standard dense Q4 model that fits at 8K context — bigger models become possible at lower context or with KV-cache quantization.

Family Chip Year RAM Bandwidth Bus Cooling Largest fit (Q4 dense, 8K ctx)
MacBook Air M1 2020 8 GB16 GB 68 GB/s 128-bit passive
8 GB 7B Q4
16 GB 14B Q4
MacBook Pro 13" M1 2020 8 GB16 GB 68 GB/s 128-bit active
8 GB 7B Q4
16 GB 14B Q4
Mac mini M1 2020 8 GB16 GB 68 GB/s 128-bit active
8 GB 7B Q4
16 GB 14B Q4
MacBook Pro 14"/16" M1 Pro 2021 16 GB32 GB 200 GB/s 256-bit active
16 GB 14B Q4
32 GB 32B Q4
MacBook Pro 14"/16" M1 Max 2021 32 GB64 GB 400 GB/s 512-bit active
32 GB 32B Q4
64 GB 70B Q4
Mac Studio M1 Ultra 2022 64 GB128 GB 800 GB/s 1024-bit active
64 GB 70B Q4
128 GB Mixtral 8x22B Q4
MacBook Air 13"/15" M2 2022 8 GB16 GB24 GB 100 GB/s 128-bit passive
8 GB 7B Q4
16 GB 14B Q4
24 GB 14B Q4
Mac mini M2 2023 8 GB16 GB24 GB 100 GB/s 128-bit active
8 GB 7B Q4
16 GB 14B Q4
24 GB 14B Q4
MacBook Pro 14"/16" M2 Pro 2023 16 GB32 GB 200 GB/s 256-bit active
16 GB 14B Q4
32 GB 32B Q4
MacBook Pro 14"/16" M2 Max 2023 32 GB64 GB96 GB 400 GB/s 512-bit active
32 GB 32B Q4
64 GB 70B Q4
96 GB 70B Q4
Mac Studio M2 Max 2023 32 GB64 GB96 GB 400 GB/s 512-bit active
32 GB 32B Q4
64 GB 70B Q4
96 GB 70B Q4
Mac Studio M2 Ultra 2023 64 GB128 GB192 GB 800 GB/s 1024-bit active
64 GB 70B Q4
128 GB Mixtral 8x22B Q4
192 GB Mixtral 8x22B Q4
MacBook Air 13"/15" M3 2024 8 GB16 GB24 GB 100 GB/s 128-bit passive
8 GB 7B Q4
16 GB 14B Q4
24 GB 14B Q4
MacBook Pro 14" M3 2023 8 GB16 GB24 GB 100 GB/s 128-bit active
8 GB 7B Q4
16 GB 14B Q4
24 GB 14B Q4
MacBook Pro 14"/16" M3 Pro
narrower bus than M2 Pro — slower decode for bandwidth-bound models
2023 18 GB36 GB 150 GB/s 192-bit active
18 GB 14B Q4
36 GB 32B Q4
MacBook Pro 14"/16" M3 Max (14-core)
binned die — 384-bit bus
2023 36 GB96 GB 300 GB/s 384-bit active
36 GB 32B Q4
96 GB 70B Q4
MacBook Pro 14"/16" M3 Max (16-core)
full die — 512-bit bus
2023 48 GB64 GB128 GB 400 GB/s 512-bit active
48 GB 32B Q4
64 GB 70B Q4
128 GB Mixtral 8x22B Q4
Mac Studio M3 Ultra
512 GB option is the consumer-hardware capacity ceiling
2025 96 GB256 GB512 GB 800 GB/s 1024-bit active
96 GB 70B Q4
256 GB Mixtral 8x22B Q4
512 GB DeepSeek-V3 Q4
MacBook Air 13"/15" M4 2025 16 GB24 GB32 GB 120 GB/s 128-bit passive
16 GB 14B Q4
24 GB 14B Q4
32 GB 32B Q4
Mac mini M4 2024 16 GB24 GB32 GB 120 GB/s 128-bit active
16 GB 14B Q4
24 GB 14B Q4
32 GB 32B Q4
MacBook Pro 14" M4 2024 16 GB24 GB32 GB 120 GB/s 128-bit active
16 GB 14B Q4
24 GB 14B Q4
32 GB 32B Q4
MacBook Pro 14"/16" M4 Pro 2024 24 GB48 GB64 GB 273 GB/s 256-bit active
24 GB 14B Q4
48 GB 32B Q4
64 GB 70B Q4
MacBook Pro 14"/16" M4 Max (14-core)
binned die — 36 GB only
2024 36 GB 410 GB/s 384-bit active
36 GB 32B Q4
MacBook Pro 14"/16" M4 Max (16-core)
biggest generational bandwidth jump in M-series
2024 48 GB64 GB128 GB 546 GB/s 512-bit active
48 GB 32B Q4
64 GB 70B Q4
128 GB Mixtral 8x22B Q4
Mac Studio M4 Max 2025 36 GB48 GB64 GB128 GB 546 GB/s 512-bit active
36 GB 32B Q4
48 GB 32B Q4
64 GB 70B Q4
128 GB Mixtral 8x22B Q4
MacBook Pro 14" M5
first Apple Silicon with neural accelerators inside each GPU core
2025 16 GB24 GB32 GB 150 GB/s 128-bit active
16 GB 14B Q4
24 GB 14B Q4
32 GB 32B Q4

Late-Intel Macs (pre-2020) are not supported — no unified memory, no MLX, no Metal-shared-storage path. See the full lineage and the M3 Pro bandwidth regression notes in the Mac hardware lineup .

App fit matrix

Locara apps, by Mac RAM tier.

Each row is an app from the catalogue, sorted by RAM floor. "Working set" is the sum of all pinned models plus the 1 GB activation overhead. The declared column is what the developer asserts in the manifest; the computed column is what the math says — we use the larger of the two as the effective floor.

App Modalities Working set Declared min Computed min Runs on
Data Analyser
kingtongchoo
text-to-texttext-to-code
1.92 GB 16 GB 8 GB
1618243236486496128 +
demo
your-publisher-id
text-to-text
1.31 GB 16 GB 8 GB
1618243236486496128 +
DocVault
kingtongchoo
text-to-texttext-to-embeddingimage-to-text
1.44 GB 16 GB 8 GB
1618243236486496128 +
Listen
kingtongchoo
text-to-textspeech-to-text
1.46 GB 16 GB 8 GB
1618243236486496128 +
Reader
kingtongchoo
text-to-texttext-to-embedding
4.67 GB 16 GB 8 GB
1618243236486496128 +
Scribe
kingtongchoo
text-to-texttext-to-code
2.83 GB 16 GB 8 GB
1618243236486496128 +
Studio
kingtongchoo
text-to-texttext-to-code
1.92 GB 16 GB 8 GB
1618243236486496128 +
Transcribe
kingtongchoo
text-to-texttext-to-embeddingspeech-to-text
1.46 GB 16 GB 8 GB
1618243236486496128 +
Video Generator
kingtongchoo
text-to-texttext-to-code
1.92 GB 16 GB 8 GB
1618243236486496128 +
Voice
kingtongchoo
text-to-textspeech-to-textvoice-to-voice
14.91 GB 16 GB 24 GB
243236486496128 +

Today every shipping app fits on a 16 GB Mac because they pin small (≤3B Q4) models. As the model registry grows to 7B and 13B classes for chat, and 7B+ for voice-omni, this matrix becomes the differentiator between "runs on any Air" and "needs a Pro." App authors should treat the declared min as a contract with the user, not an estimate.

Models in the catalogue

What's pinned, by whom, at what cost.

Models in Locara are content-addressed and shared across apps. Every model below is referenced by at least one shipping app's manifest. Weight cost is approximate; see llm-memory-math for the underlying formula.

Model Modality Params Quant (bpw) Weight Used by
BGE Small en v1.5
bge-small-en-v1.5
embed 0.033B 16.00 0.13 GB
Whisper base.en
whisper-base.en
stt 0.074B 16.00 0.15 GB
Qwen 2.5 0.5B
qwen2.5-0.5b-instruct-q4
chat 0.5B 4.89 0.31 GB
Qwen 2.5 1.5B
qwen2.5-1.5b-instruct-q4
chat 1.5B 4.89 0.92 GB
Qwen 2.5 1.5B
qwen2.5-1.5b-instruct-q4_k_m
chat 1.5B 4.89 0.92 GB
Qwen 2.5 Coder 3B
qwen2.5-coder-3b-instruct-q4
code 3B 4.89 1.83 GB
Qwen 3.5 4B
qwen3.5-4b-instruct-q4_k_m
chat 4B 4.89 2.44 GB
Kyutai Moshi 7B
moshi-7b
voice 7B 4.89 4.28 GB
Personaplex 7B
personaplex-7b
voice 7B 4.89 4.28 GB
Qwen Omni 7B
qwen-omni-7b
voice 7B 4.89 4.28 GB
Caveats

Three things the table doesn't show.