// model_catalog
Curated the hard way: we ran
30
candidates through the same on-device tests and kept the
13
that earned a place.
Every one is quantized for Apple Silicon and runs fully on-device. LFM3 1.7B ships inside the
app; the rest download from Hugging Face. Grouped by where it runs, then by family — memory
figures are on-device peaks, weights are download size.
9 models
Models that fit within iOS's ~5 GB per-app memory budget. “Tight” models still run, but sit close to the limit on some devices.
Qwen
4
Qwen2.5 0.5B Instruct (4-bit)
Ultra-light chat and quick PDF Q&A; long answers cut off
Limited
- RAM peak
- 1.5–2.3 GB
- Weights
- 0.27 GB
- Context
-
32,768 tok*
- Min Mac RAM
- 8 GB
Alibaba (Qwen)
Apache 2.0
Qwen3 0.6B (4-bit)
Fast reasoning, PDF Q&A, and doc lookup at a tiny size
Capable
- RAM peak
- 1.5–2.3 GB
- Weights
- 0.33 GB
- Context
-
40,960 tok*
- Min Mac RAM
- 8 GB
Reasoning
Alibaba (Qwen)
Apache 2.0
Qwen3 1.7B (4-bit)
Reasoning plus accurate doc lookup in a light model
Strong
- RAM peak
- 2.1–2.9 GB
- Weights
- 0.92 GB
- Context
-
40,960 tok*
- Min Mac RAM
- 8 GB
Reasoning
Alibaba (Qwen)
Apache 2.0
Qwen3 4B Instruct 2507 (4-bit)
Top all-rounder — reasoning and PDF tools; passed every test
Strongest
- RAM peak
- 3.3–4.1 GB
- Weights
- 2.12 GB
- Context
-
262,144 tok*
- Min Mac RAM
- 8 GB
Reasoning
Tools
Lookups
Documents
Alibaba (Qwen)
Apache 2.0
LFM (Liquid AI)
2
LFM2.5 1.2B Instruct (4-bit)
Fast, dependable chat and PDF/doc Q&A (Liquid AI)
Capable
- RAM peak
- 1.8–2.6 GB
- Weights
- 0.62 GB
- Context
-
128,000 tok*
- Min Mac RAM
- 8 GB
LFM3 1.7B (4-bit)
Reasoning, tool use and doc Q&A at 1.7B (Liquid AI)
Strongest
- RAM peak
- 2.2–3.0 GB
- Weights
- 0.97 GB
- Context
-
262,144 tok*
- Min Mac RAM
- 8 GB
Reasoning
Tools
Lookups
Documents
SmolLM
1
SmolLM3 3B (4-bit)
Reasoning, PDFs, and doc lookup — passed every on-device test
Strongest
- RAM peak
- 2.9–3.7 GB
- Weights
- 1.67 GB
- Context
-
65,536 tok*
- Min Mac RAM
- 8 GB
Reasoning
Tools
Documents
Nemotron
1
Nemotron 3 Nano 4B (4-bit)
Reasoning and doc Q&A — near-perfect in tests
Capable
- RAM peak
- 3.2–4.0 GB
- Weights
- 2.24 GB
- Context
-
262,144 tok*
- Min Mac RAM
- 8 GB
Reasoning
Tools
Lookups
Documents
Ministral
1
Ministral 3 3B Instruct (4-bit)
Compact instruction-following chat and doc Q&A
Capable
- RAM peak
- 3.8–4.6 GB
- Weights
- 2.59 GB
- Context
-
262,144 tok*
- Min Mac RAM
- 8 GB
Tools
Documents
13 models
Every catalog model runs on a Mac with enough memory — the card shows the minimum RAM each one needs.
Qwen
5
Qwen2.5 0.5B Instruct (4-bit)
Ultra-light chat and quick PDF Q&A; long answers cut off
Limited
- RAM peak
- 1.5–2.3 GB
- Weights
- 0.27 GB
- Context
-
32,768 tok*
- Min Mac RAM
- 8 GB
Alibaba (Qwen)
Apache 2.0
Qwen3 0.6B (4-bit)
Fast reasoning, PDF Q&A, and doc lookup at a tiny size
Capable
- RAM peak
- 1.5–2.3 GB
- Weights
- 0.33 GB
- Context
-
40,960 tok*
- Min Mac RAM
- 8 GB
Reasoning
Alibaba (Qwen)
Apache 2.0
Qwen3 1.7B (4-bit)
Reasoning plus accurate doc lookup in a light model
Strong
- RAM peak
- 2.1–2.9 GB
- Weights
- 0.92 GB
- Context
-
40,960 tok*
- Min Mac RAM
- 8 GB
Reasoning
Alibaba (Qwen)
Apache 2.0
Qwen3 4B Instruct 2507 (4-bit)
Top all-rounder — reasoning and PDF tools; passed every test
Strongest
- RAM peak
- 3.3–4.1 GB
- Weights
- 2.12 GB
- Context
-
262,144 tok*
- Min Mac RAM
- 8 GB
Reasoning
Tools
Lookups
Documents
Alibaba (Qwen)
Apache 2.0
Qwen3 8B (4-bit)
Strongest reasoning in class — passed every on-device test
Strongest
- RAM peak
- 5.5–6.3 GB
- Weights
- 4.31 GB
- Context
-
40,960 tok*
- Min Mac RAM
- 16 GB
Mac only
Reasoning
Tools
Lookups
Documents
Alibaba (Qwen)
Apache 2.0
LFM (Liquid AI)
2
LFM2.5 1.2B Instruct (4-bit)
Fast, dependable chat and PDF/doc Q&A (Liquid AI)
Capable
- RAM peak
- 1.8–2.6 GB
- Weights
- 0.62 GB
- Context
-
128,000 tok*
- Min Mac RAM
- 8 GB
LFM3 1.7B (4-bit)
Reasoning, tool use and doc Q&A at 1.7B (Liquid AI)
Strongest
- RAM peak
- 2.2–3.0 GB
- Weights
- 0.97 GB
- Context
-
262,144 tok*
- Min Mac RAM
- 8 GB
Reasoning
Tools
Lookups
Documents
SmolLM
1
SmolLM3 3B (4-bit)
Reasoning, PDFs, and doc lookup — passed every on-device test
Strongest
- RAM peak
- 2.9–3.7 GB
- Weights
- 1.67 GB
- Context
-
65,536 tok*
- Min Mac RAM
- 8 GB
Reasoning
Tools
Documents
Nemotron
3
Nemotron 3 Nano 4B (4-bit)
Reasoning and doc Q&A — near-perfect in tests
Capable
- RAM peak
- 3.2–4.0 GB
- Weights
- 2.24 GB
- Context
-
262,144 tok*
- Min Mac RAM
- 8 GB
Reasoning
Tools
Lookups
Documents
Llama Nemotron 8B UltraLong 1M (4-bit)
Long-context reasoning and doc Q&A on Mac
Strong
- RAM peak
- 5.5–6.3 GB
- Weights
- 4.52 GB
- Context
-
1,073,152 tok*
- Min Mac RAM
- 16 GB
Mac only
Reasoning
Tools
Lookups
Documents
Nemotron Nano 9B v2 (4-bit)
Reasoning and docs — passed every on-device test
Strong
- RAM peak
- 6.0–6.8 GB
- Weights
- 5.0 GB
- Context
-
131,072 tok*
- Min Mac RAM
- 16 GB
Mac only
Reasoning
Tools
Lookups
Documents
Ministral
1
Ministral 3 3B Instruct (4-bit)
Compact instruction-following chat and doc Q&A
Capable
- RAM peak
- 3.8–4.6 GB
- Weights
- 2.59 GB
- Context
-
262,144 tok*
- Min Mac RAM
- 8 GB
Tools
Documents
Phi
1
Phi-4 (3-bit)
High-accuracy reasoning and math on Mac
Strongest
- RAM peak
- 7.0–7.8 GB
- Weights
- 5.98 GB
- Context
-
16,384 tok*
- Min Mac RAM
- 16 GB
Mac only
Standings describe how each conversion behaves inside Mortise — not a general
benchmark of the underlying model.
How this was measured
* Context is the developer’s advertised maximum, not the window Mortise will give you.
The app calculates that at runtime — up to the listed figure, if your hardware has the headroom.
// buy_once
No subscription, no account, no server of ours. Every update included.