Compatibility route: WorthCompatibility route

Which models are practical on Mac Mini M4 24GB?

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

This route presets the rankings around local-cost reading rather than splitting worth into its own product.

Snapshot

Top model: Qwen 3 0.6B

25 viable rows · 3 measured directly · 184.4 tok/s at Q8_0.

Rows: 251
Models: 33
Macs: 28
Measured: 3

Catalog current through February 27, 2026

Raw data Models Chips

Query setup

Audit evidence

Choose a Mac first, then narrow by lens, quant target, runtime, and ranking preference.

Mac

Capability

Quant target

Runtime

Sort

Results

Model matches for Mac Mini M4 24GB

Sorted by lowest local cost · 25 viable rows · 3 measured directly

Viable rows: 25
Direct benchmark-backed: 3

ModelOutputPromptQuantRuntimeHeadroomContextCost readDetail

#1EstimatedLow confidence

Qwen 3 0.6B

Mac Mini M4 24GB · 24GB · $599 · Desktop

Output184.4 tok/s

Prompt—

QuantQ8_0

RuntimeLM Studio

Headroom21.4 GB

Context10k

Local cost$0.347

Detail Open

Capability

0.6B dense · general-purpose

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: LM Studio.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality21.4 GB33k184.4 tok/sLM StudioEstimated

Q6_KHigh quality21.5 GB33k184.4 tok/sLM StudioEstimated

Q5_K_MHigh quality21.6 GB33k184.4 tok/sLM StudioEstimated

Q4_K_MBalanced quality21.7 GB33k184.4 tok/sLM StudioEstimated

#2EstimatedLow confidence

Qwen 3 4B

Mac Mini M4 24GB · 24GB · $599 · Desktop

Output143.2 tok/s

Prompt2754.5 tok/s

QuantQ8_0

RuntimeMLX

Headroom18.0 GB

Context2k

Local cost$0.447

Detail Open

Capability

4.02B dense · general-purpose

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

Q8_0Reference quality18.0 GB33k143.2 tok/sMLXEstimated

Q6_KHigh quality18.7 GB33k143.2 tok/sMLXEstimated

Q5_K_MHigh quality19.1 GB33k143.2 tok/sMLXEstimated

Q4_K_MBalanced quality19.7 GB33k143.2 tok/sMLXEstimated

#3MeasuredLow confidence

Llama 3.2 1B

Mac Mini M4 24GB · 24GB · $599 · Desktop

Output110.9 tok/s

Prompt1823.8 tok/s

QuantQ8_0

RuntimeLlamafile

Headroom20.8 GB

Context131k

Local cost$0.577

Detail Open

Capability

1.24B dense · general-purpose

Evidence

Direct benchmark coverage on this hardware class Speed is backed by direct benchmark coverage. Most common runtime in the evidence is Llamafile.

Coverage

3 direct benchmark rows

Default 10% utilization napkin math.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality20.8 GB131k110.9 tok/sLlamafileMeasured

Q6_KHigh quality21.0 GB131k110.9 tok/sLlamafileMeasured

Q5_K_MHigh quality21.1 GB131k110.9 tok/sLlamafileMeasured

Q4_K_MBalanced quality21.3 GB131k110.9 tok/sLlamafileMeasured

#4EstimatedLow confidence

Gemma 3 4B

Mac Mini M4 24GB · 24GB · $599 · Desktop

Output100.5 tok/s

Prompt—

QuantQ8_0

RuntimeLM Studio

Headroom17.7 GB

Context4k

Local cost$0.637

Detail Open

Capability

4.3B dense · adjacent fit 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: LM Studio.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality17.7 GB131k100.5 tok/sLM StudioEstimated

Q6_KHigh quality18.5 GB131k100.5 tok/sLM StudioEstimated

Q5_K_MHigh quality18.9 GB131k100.5 tok/sLM StudioEstimated

Q4_K_MBalanced quality19.5 GB131k100.5 tok/sLM StudioEstimated

#5EstimatedLow confidence

Qwen 3 30B-A3B

Mac Mini M4 24GB · 24GB · $599 · Desktop

Output70.2 tok/s

Prompt—

QuantQ4_K_M

RuntimeLM Studio

Headroom4.5 GB

Context10k

Local cost$0.912

Detail Open

Capability

30.53B total · 3.3B active · 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: LM Studio.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q4_K_MBalanced quality4.5 GB49k70.2 tok/sLM StudioEstimated

#6EstimatedLow confidence

Qwen 3 8B

Mac Mini M4 24GB · 24GB · $599 · Desktop

Output63.1 tok/s

Prompt—

QuantQ8_0

RuntimeLM Studio

Headroom13.8 GB

Context10k

Local cost$1.01

Detail Open

Capability

8.19B dense · general-purpose

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: LM Studio.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality13.8 GB101k63.1 tok/sLM StudioEstimated

Q6_KHigh quality15.3 GB111k63.1 tok/sLM StudioEstimated

Q5_K_MHigh quality16.2 GB118k63.1 tok/sLM StudioEstimated

Q4_K_MBalanced quality17.3 GB126k63.1 tok/sLM StudioEstimated

#7EstimatedLow confidence

Qwen3-Coder-30B-A3B

Mac Mini M4 24GB · 24GB · $599 · Desktop

Output58.5 tok/s

Prompt132.1 tok/s

QuantQ4_K_M

Runtimellama.cpp

Headroom4.5 GB

Context4k

Local cost$1.09

Detail Open

Capability

30.53B total · 3.3B active · 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

Q4_K_MBalanced quality4.5 GB99k58.5 tok/sllama.cppEstimated

#8EstimatedLow confidence

Qwen 2.5 7B

Mac Mini M4 24GB · 24GB · $599 · Desktop

Output49.7 tok/s

Prompt—

QuantQ8_0

RuntimeLM Studio

Headroom14.4 GB

Context10k

Local cost$1.29

Detail Open

Capability

7.62B dense · general-purpose

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: LM Studio.

Coverage

No direct benchmark rows yet

Speed is estimated, so this cost read is provisional.

Quant ladder and fit detail

QuantQualityHeadroomContextSpeedRuntimeEvidence

Q8_0Reference quality14.4 GB131k49.7 tok/sLM StudioEstimated

Q6_KHigh quality15.8 GB131k49.7 tok/sLM StudioEstimated

Q5_K_MHigh quality16.6 GB131k49.7 tok/sLM StudioEstimated

Q4_K_MBalanced quality17.6 GB131k49.7 tok/sLM StudioEstimated