Pick Apple Foundation Models 3 for runs entirely on-device on iphone - no api call, no per-token cost, works offline or the 20b sparse 'core advanced' variant lifted on-device output quality from 23% to 46% user preference in apple's own testing versus the prior generation. Pick MiniMax M2.7 for agentic and terminal coding well above its price tier (57.0 on terminal-bench 2, vendor-reported) or independently ranked 14th of 97 on the artificial analysis intelligence index. Choose MiniMax M2.7 if you need self-hosting or data privacy; Apple Foundation Models 3 if you want a managed API.
Apple Foundation Models 3 (Apple, US) and MiniMax M2.7 (MiniMax, China) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. Apple Foundation Models 3 is apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone. MiniMax M2.7 is a cheap open-weight agentic coder with near-frontier terminal scores — held back by a non-commercial licence and non-standard benchmarks. They diverge most on price, context window and open vs. closed weights — each quantified below from the models' real specs.
Key differences
Cost model: MiniMax M2.7 ships open weights you can self-host (hardware cost only, no per-token fee), while Apple Foundation Models 3 is API-metered at Not published. Your choice depends on whether you want zero marginal cost at the price of running infrastructure.
Context window: MiniMax M2.7 holds 50× more — 205K (~307 pages) vs 4K (~6 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
Recency: Apple Foundation Models 3 is the newer model by about 3 months (released June 2026), usually meaning fresher training data and capabilities.
Ecosystem: this is a US-vs-China matchup — they differ in pricing philosophy, data-residency options, and tooling ecosystems, not only benchmarks.
Specifications
Spec
Apple Foundation Models 3
MiniMax M2.7
Provider
Apple (US)
MiniMax (China)
Released
June 2026
March 18, 2026
Context window
4K (~6 pages)
205K (~307 pages)
Price (in/out)
Not published
$0.3/$1.2 per 1M tokens
Open weight?
No — API only
Yes — self-hostable
Modalities
text, image
text, code
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Runs entirely on-device on iPhone - no API call, no per-token cost, works offline: Apple Foundation Models 3 — Apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone — and it is the newer of the two.
The 20B sparse 'Core Advanced' variant lifted on-device output quality from 23% to 46% user preference in Apple's own testing versus the prior generation: Apple Foundation Models 3 — MiniMax M2.7 is comparatively weak here — open weights but a NON-COMMERCIAL licence — commercial use requires prior written authorisation from MiniMax, and at least one major tracker still mislabels it as MIT
Deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too: Apple Foundation Models 3 — Apple Foundation Models 3 lists deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too among its strengths; MiniMax M2.7 does not.
Agentic and terminal coding well above its price tier (57.0 on Terminal-Bench 2, vendor-reported): MiniMax M2.7 — Apple Foundation Models 3 is comparatively weak here — not comparable in raw capability to frontier cloud models - built for efficiency and privacy, not benchmark leadership
Independently ranked 14th of 97 on the Artificial Analysis Intelligence Index: MiniMax M2.7 — A cheap open-weight agentic coder with near-frontier terminal scores — held back by a non-commercial licence and non-standard benchmarks — and it carries the larger 205K context.
Sparse mixture-of-experts — roughly 230B total but only ~10B active, so it runs on local hardware: MiniMax M2.7 — Open weights make this possible at all — Apple Foundation Models 3 is API-only, so it cannot leave the vendor's servers.
Lowest cost at scale: Apple Foundation Models 3 — Its weights are open, so at volume you pay for your own hardware instead of MiniMax M2.7's $0.3/$1.2 per 1M tokens.
Largest single-prompt input: MiniMax M2.7 — Its 205K window is about 50× larger than Apple Foundation Models 3's 4K, fitting roughly 307 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume: Apple Foundation Models 3 — At Not published it undercuts MiniMax M2.7, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases: MiniMax M2.7 — Larger 205K window fits more in one prompt.
A team with data-privacy or self-hosting needs: MiniMax M2.7 — Open weights let you run it on your own hardware; Apple Foundation Models 3 is API-only.
Anyone whose priority is runs entirely on-device on iphone - no api call, no per-token cost, works offline: Apple Foundation Models 3 — It is specifically built for that.
Anyone whose priority is agentic and terminal coding well above its price tier (57.0 on terminal-bench 2, vendor-reported): MiniMax M2.7 — That is its strongest area.
An enterprise with regional data-residency rules: Apple Foundation Models 3 or MiniMax M2.7 — Origin (US vs China) affects where data is processed and which compliance regime applies — check the provider's terms for your region.
Apple Foundation Models 3: where it fits
Apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone. Released June 2026 by Apple, it is built for runs entirely on-device on iPhone - no API call, no per-token cost, works offline, the 20B sparse 'Core Advanced' variant lifted on-device output quality from 23% to 46% user preference in Apple's own testing versus the prior generation, deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too, and zero marginal cost and strong privacy - nothing leaves the device.
Its trade-offs are real: a genuinely small context window (about 4,096 tokens, shared between input and output) - far below cloud frontier models, not comparable in raw capability to frontier cloud models - built for efficiency and privacy, not benchmark leadership, and no public API pricing since it isn't sold per-token - only usable within Apple's own platforms.
MiniMax M2.7: where it fits
A cheap open-weight agentic coder with near-frontier terminal scores — held back by a non-commercial licence and non-standard benchmarks. Released March 18, 2026 by MiniMax, it is built for agentic and terminal coding well above its price tier (57.0 on Terminal-Bench 2, vendor-reported), independently ranked 14th of 97 on the Artificial Analysis Intelligence Index, sparse mixture-of-experts — roughly 230B total but only ~10B active, so it runs on local hardware, and served by five separate hosts at uniform pricing, so there is no provider lock-in.
Its trade-offs: open weights but a NON-COMMERCIAL licence — commercial use requires prior written authorisation from MiniMax, and at least one major tracker still mislabels it as MIT, reports SWE-Bench Pro instead of the standard Verified set, which blocks like-for-like comparison, and already superseded internally by M3, and its 205K context is small against 1M-class rivals. At $0.3 in / $1.2 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
The defining split here is open vs. closed. MiniMax M2.7 gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Apple Foundation Models 3 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Frequently asked questions
Is Apple Foundation Models 3 or MiniMax M2.7 better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Apple Foundation Models 3 leans toward runs entirely on-device on iphone - no api call, no per-token cost, works offline while MiniMax M2.7 leans toward agentic and terminal coding well above its price tier (57.0 on terminal-bench 2, vendor-reported), and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Apple Foundation Models 3 or MiniMax M2.7?
MiniMax M2.7 is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Apple Foundation Models 3 is API-metered at Not published. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
MiniMax M2.7 — 205K vs 4K, about 50× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both Apple Foundation Models 3 and MiniMax M2.7 together?
Yes — a multi-model platform like LumiChats gives you Apple Foundation Models 3, MiniMax M2.7 and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, Apple Foundation Models 3 or MiniMax M2.7?
Apple Foundation Models 3 — released June 2026, about 3 months after MiniMax M2.7.
Apple Foundation Models 3 vs MiniMax M2.7
Apple · US | MiniMax · China · Updated June 2026
Quick verdict
Pick Apple Foundation Models 3 for runs entirely on-device on iphone - no api call, no per-token cost, works offline or the 20b sparse 'core advanced' variant lifted on-device output quality from 23% to 46% user preference in apple's own testing versus the prior generation. Pick MiniMax M2.7 for agentic and terminal coding well above its price tier (57.0 on terminal-bench 2, vendor-reported) or independently ranked 14th of 97 on the artificial analysis intelligence index. Choose MiniMax M2.7 if you need self-hosting or data privacy; Apple Foundation Models 3 if you want a managed API.
Apple Foundation Models 3 (Apple, US) and MiniMax M2.7 (MiniMax, China) line up two different AI ecosystems against each other — a comparison that is as much about cost philosophy and openness as raw capability. Apple Foundation Models 3 is apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone. MiniMax M2.7 is a cheap open-weight agentic coder with near-frontier terminal scores — held back by a non-commercial licence and non-standard benchmarks. They diverge most on price, context window and open vs. closed weights — each quantified below from the models' real specs.
Key differences at a glance
▸Cost model: MiniMax M2.7 ships open weights you can self-host (hardware cost only, no per-token fee), while Apple Foundation Models 3 is API-metered at Not published. Your choice depends on whether you want zero marginal cost at the price of running infrastructure.
▸Context window: MiniMax M2.7 holds 50× more — 205K (~307 pages) vs 4K (~6 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
▸Recency: Apple Foundation Models 3 is the newer model by about 3 months (released June 2026), usually meaning fresher training data and capabilities.
▸Ecosystem: this is a US-vs-China matchup — they differ in pricing philosophy, data-residency options, and tooling ecosystems, not only benchmarks.
Side-by-side specs
Spec
Apple Foundation Models 3
MiniMax M2.7
Provider
Apple (US)
MiniMax (China)
Released
June 2026
March 18, 2026
Context window
4K (~6 pages)
205K (~307 pages)
Price (in/out)
Not published
$0.3/$1.2 per 1M tokens
Open weight?
No — API only
Yes — self-hostable
Modalities
text, image
text, code
SWE-Bench Verified
Not published
Not published
MRCR v2 @ 1M
Not published
Not published
Who wins what
Runs entirely on-device on iPhone - no API call, no per-token cost, works offline
Apple Foundation Models 3
Apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone — and it is the newer of the two.
The 20B sparse 'Core Advanced' variant lifted on-device output quality from 23% to 46% user preference in Apple's own testing versus the prior generation
Apple Foundation Models 3
MiniMax M2.7 is comparatively weak here — open weights but a NON-COMMERCIAL licence — commercial use requires prior written authorisation from MiniMax, and at least one major tracker still mislabels it as MIT
Deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too
Apple Foundation Models 3
Apple Foundation Models 3 lists deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too among its strengths; MiniMax M2.7 does not.
Agentic and terminal coding well above its price tier (57.0 on Terminal-Bench 2, vendor-reported)
MiniMax M2.7
Apple Foundation Models 3 is comparatively weak here — not comparable in raw capability to frontier cloud models - built for efficiency and privacy, not benchmark leadership
Independently ranked 14th of 97 on the Artificial Analysis Intelligence Index
MiniMax M2.7
A cheap open-weight agentic coder with near-frontier terminal scores — held back by a non-commercial licence and non-standard benchmarks — and it carries the larger 205K context.
Sparse mixture-of-experts — roughly 230B total but only ~10B active, so it runs on local hardware
MiniMax M2.7
Open weights make this possible at all — Apple Foundation Models 3 is API-only, so it cannot leave the vendor's servers.
Lowest cost at scale
Apple Foundation Models 3
Its weights are open, so at volume you pay for your own hardware instead of MiniMax M2.7's $0.3/$1.2 per 1M tokens.
Largest single-prompt input
MiniMax M2.7
Its 205K window is about 50× larger than Apple Foundation Models 3's 4K, fitting roughly 307 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Apple Foundation Models 3
At Not published it undercuts MiniMax M2.7, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ MiniMax M2.7
Larger 205K window fits more in one prompt.
A team with data-privacy or self-hosting needs
→ MiniMax M2.7
Open weights let you run it on your own hardware; Apple Foundation Models 3 is API-only.
Anyone whose priority is runs entirely on-device on iphone - no api call, no per-token cost, works offline
→ Apple Foundation Models 3
It is specifically built for that.
Anyone whose priority is agentic and terminal coding well above its price tier (57.0 on terminal-bench 2, vendor-reported)
→ MiniMax M2.7
That is its strongest area.
An enterprise with regional data-residency rules
→ Apple Foundation Models 3 or MiniMax M2.7
Origin (US vs China) affects where data is processed and which compliance regime applies — check the provider's terms for your region.
Apple Foundation Models 3: where it fits
Apple's on-device model family - genuinely small context and no API access, but private, offline, and free to run on every iPhone. Released June 2026 by Apple, it is built for runs entirely on-device on iPhone - no API call, no per-token cost, works offline, the 20B sparse 'Core Advanced' variant lifted on-device output quality from 23% to 46% user preference in Apple's own testing versus the prior generation, deep integration with iOS apps via the Foundation Models framework, now open to third-party LLM providers too, and zero marginal cost and strong privacy - nothing leaves the device.
Its trade-offs are real: a genuinely small context window (about 4,096 tokens, shared between input and output) - far below cloud frontier models, not comparable in raw capability to frontier cloud models - built for efficiency and privacy, not benchmark leadership, and no public API pricing since it isn't sold per-token - only usable within Apple's own platforms.
MiniMax M2.7: where it fits
A cheap open-weight agentic coder with near-frontier terminal scores — held back by a non-commercial licence and non-standard benchmarks. Released March 18, 2026 by MiniMax, it is built for agentic and terminal coding well above its price tier (57.0 on Terminal-Bench 2, vendor-reported), independently ranked 14th of 97 on the Artificial Analysis Intelligence Index, sparse mixture-of-experts — roughly 230B total but only ~10B active, so it runs on local hardware, and served by five separate hosts at uniform pricing, so there is no provider lock-in.
Its trade-offs: open weights but a NON-COMMERCIAL licence — commercial use requires prior written authorisation from MiniMax, and at least one major tracker still mislabels it as MIT, reports SWE-Bench Pro instead of the standard Verified set, which blocks like-for-like comparison, and already superseded internally by M3, and its 205K context is small against 1M-class rivals. At $0.3 in / $1.2 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
The defining split here is open vs. closed. MiniMax M2.7 gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Apple Foundation Models 3 gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Want both Apple Foundation Models 3 and MiniMax M2.7 without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
Is Apple Foundation Models 3 or MiniMax M2.7 better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Apple Foundation Models 3 leans toward runs entirely on-device on iphone - no api call, no per-token cost, works offline while MiniMax M2.7 leans toward agentic and terminal coding well above its price tier (57.0 on terminal-bench 2, vendor-reported), and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Apple Foundation Models 3 or MiniMax M2.7?
MiniMax M2.7 is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Apple Foundation Models 3 is API-metered at Not published. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
MiniMax M2.7 — 205K vs 4K, about 50× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both Apple Foundation Models 3 and MiniMax M2.7 together?
Yes — a multi-model platform like LumiChats gives you Apple Foundation Models 3, MiniMax M2.7 and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, Apple Foundation Models 3 or MiniMax M2.7?
Apple Foundation Models 3 — released June 2026, about 3 months after MiniMax M2.7.
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.