Compatibility route: BuyCompatibility route

Which Macs run Qwen3.5-27B?

Current lens: Coding. Rank Macs by cheapest viable, while keeping throughput, fit, local cost, and evidence on the same sheet.

This route remains live for compatibility, but the product center is now the canonical rankings surface.

Snapshot

Top Mac: Mac Mini M4 24GB

25 viable rows · 4 measured directly · 8.5 tok/s at Q5_K_M.

Rows: 251
Models: 33
Macs: 28
Measured: 4

Catalog current through February 27, 2026

Raw data Models Chips

Query setup

Audit evidence

Choose a target model first, then narrow by lens, quant target, runtime, and portability.

Model

Capability

Quant target

Runtime

Form factor

Sort

Results

Mac matches for Qwen3.5-27B

Sorted by cheapest viable · 25 viable rows · 4 measured directly

Viable rows: 25
Direct benchmark-backed: 4

MacOutputPromptQuantRuntimeHeadroomContextCost readDetail

#1EstimatedLow confidence

Mac Mini M4 24GB

M4 · 24GB unified memory · $599 · Desktop

Output8.5 tok/s

Prompt—

QuantQ5_K_M

Runtimellama.cpp

Headroom2.8 GB

Context11k

Local cost$7.53

Detail Open

Capability

27B dense · tuned for coding

Evidence

Estimated from nearby benchmark coverage, not a direct match Speed is estimated from nearby benchmark coverage rather than this exact machine-and-quant match. Best runtime hint: llama.cpp.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q5_K_MHigh quality2.8 GB11k8.5 tok/sllama.cppEstimated

Q4_K_MBalanced quality6.5 GB27k0.0 tok/sllama.cppEstimated

#2EstimatedLow confidence

Mac Mini M4 32GB

M4 · 32GB unified memory · $799 · Desktop

Output8.5 tok/s

Prompt—

QuantQ8_0

Runtimellama.cpp

Headroom3.0 GB

Context12k

Local cost$10.0

Detail Open

Capability

27B dense · tuned for coding

Evidence

Estimated from nearby benchmark coverage, not a direct match Speed is estimated from nearby benchmark coverage rather than this exact machine-and-quant match. Best runtime hint: llama.cpp.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality3.0 GB12k8.5 tok/sllama.cppEstimated

Q6_KHigh quality7.9 GB32k8.5 tok/sllama.cppEstimated

Q5_K_MHigh quality10.8 GB44k8.5 tok/sllama.cppEstimated

Q4_K_MBalanced quality14.5 GB60k0.0 tok/sllama.cppEstimated

#3EstimatedLow confidence

MacBook Air M4 24GB 13-inch

M4 · 24GB unified memory · $1,299 · Ultra-portable

Output8.5 tok/s

Prompt—

QuantQ5_K_M

Runtimellama.cpp

Headroom2.8 GB

Context11k

Local cost$16.2

Detail Open

Capability

27B dense · tuned for coding

Evidence

Estimated from nearby benchmark coverage, not a direct match Speed is estimated from nearby benchmark coverage rather than this exact machine-and-quant match. Best runtime hint: llama.cpp.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q5_K_MHigh quality2.8 GB11k8.5 tok/sllama.cppEstimated

Q4_K_MBalanced quality6.5 GB27k0.0 tok/sllama.cppEstimated

#4EstimatedLow confidence

Mac Mini M4 Pro 24GB

M4-PRO · 24GB unified memory · $1,399 · Desktop

Output8.5 tok/s

Prompt—

QuantQ5_K_M

RuntimeMLX

Headroom2.8 GB

Context11k

Local cost$17.5

Detail Open

Capability

27B dense · tuned for coding

Evidence

Estimated from nearby benchmark coverage, not a direct match Speed is estimated from nearby benchmark coverage rather than this exact machine-and-quant match. Best runtime hint: MLX.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q5_K_MHigh quality2.8 GB11k8.5 tok/sMLXEstimated

Q4_K_MBalanced quality6.5 GB27k8.5 tok/sMLXEstimated

#5EstimatedLow confidence

MacBook Air M4 24GB 15-inch

M4 · 24GB unified memory · $1,499 · Ultra-portable

Output8.5 tok/s

Prompt—

QuantQ5_K_M

Runtimellama.cpp

Headroom2.8 GB

Context11k

Local cost$18.7

Detail Open

Capability

27B dense · tuned for coding

Evidence

Estimated from nearby benchmark coverage, not a direct match Speed is estimated from nearby benchmark coverage rather than this exact machine-and-quant match. Best runtime hint: llama.cpp.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q5_K_MHigh quality2.8 GB11k8.5 tok/sllama.cppEstimated

Q4_K_MBalanced quality6.5 GB27k0.0 tok/sllama.cppEstimated

#6EstimatedLow confidence

MacBook Air M4 32GB 13-inch

M4 · 32GB unified memory · $1,499 · Ultra-portable

Output8.5 tok/s

Prompt—

QuantQ8_0

Runtimellama.cpp

Headroom3.0 GB

Context12k

Local cost$18.7

Detail Open

Capability

27B dense · tuned for coding

Evidence

Estimated from nearby benchmark coverage, not a direct match Speed is estimated from nearby benchmark coverage rather than this exact machine-and-quant match. Best runtime hint: llama.cpp.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality3.0 GB12k8.5 tok/sllama.cppEstimated

Q6_KHigh quality7.9 GB32k8.5 tok/sllama.cppEstimated

Q5_K_MHigh quality10.8 GB44k8.5 tok/sllama.cppEstimated

Q4_K_MBalanced quality14.5 GB60k0.0 tok/sllama.cppEstimated

#7MeasuredInsufficient data

Mac Mini M4 Pro 48GB

M4-PRO · 48GB unified memory · $1,599 · Desktop

Output8.5 tok/s

Prompt—

QuantQ8_0

RuntimeMLX

Headroom19.0 GB

Context78k

Local cost$20.0

Detail Open

Capability

27B dense · tuned for coding

Evidence

Single direct benchmark anchor on this hardware class Speed is backed by direct benchmark coverage. Most common runtime in the evidence is MLX.

Coverage

1 direct benchmark row

Default 10% utilization napkin math.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality19.0 GB78k8.5 tok/sMLXMeasured

Q6_KHigh quality23.9 GB98k8.5 tok/sMLXMeasured

Q5_K_MHigh quality26.8 GB110k8.5 tok/sMLXMeasured

Q4_K_MBalanced quality30.5 GB125k8.5 tok/sMLXMeasured

#8EstimatedLow confidence

MacBook Air M4 32GB 15-inch

M4 · 32GB unified memory · $1,699 · Ultra-portable

Output8.5 tok/s

Prompt—

QuantQ8_0

Runtimellama.cpp

Headroom3.0 GB

Context12k

Local cost$21.2

Detail Open

Capability

27B dense · tuned for coding

Evidence

Estimated from nearby benchmark coverage, not a direct match Speed is estimated from nearby benchmark coverage rather than this exact machine-and-quant match. Best runtime hint: llama.cpp.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality3.0 GB12k8.5 tok/sllama.cppEstimated

Q6_KHigh quality7.9 GB32k8.5 tok/sllama.cppEstimated

Q5_K_MHigh quality10.8 GB44k8.5 tok/sllama.cppEstimated

Q4_K_MBalanced quality14.5 GB60k0.0 tok/sllama.cppEstimated