RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Will it run? / Apple Mac Studio (M3 Ultra)

What can Apple Mac Studio (M3 Ultra) run?

Build: Mac Studio M3 Ultra 256GB

Memory: 256 GB unified memory
Runner: MLX-LM (Apple Metal)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
300 models

Full-VRAM resident, with room for context. No compromises.

#1all-MiniLM-L6-v2
0.022B
other
Commercial OK
Quant: Q4_K_MContext: 256VRAM: 0.5 GBHeadroom: 247.5 GB
33126
tok/s
Estimated
Weights
0.01 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
0.50 GB
Model details →
#2Piper
0.025B
other
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 0.5 GBHeadroom: 247.5 GB
29151
tok/s
Estimated
Weights
0.02 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
0.50 GB
Model details →
#3Whisper Tiny
0.039B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 0.5 GBHeadroom: 247.5 GB
18687
tok/s
Estimated
Weights
0.02 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
0.50 GB
Model details →
#4Whisper Base
0.074B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 0.5 GBHeadroom: 247.5 GB
9848
tok/s
Estimated
Weights
0.04 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
0.50 GB
Model details →
#5Kokoro 82M
0.082B
other
Commercial OK
Quant: Q4_K_MContext: 0VRAM: 0.6 GBHeadroom: 247.4 GB
8888
tok/s
Estimated
Weights
0.05 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
0.50 GB
Model details →
#6all-mpnet-base-v2
0.109B
other
Commercial OK
Quant: Q4_K_MContext: 384VRAM: 0.6 GBHeadroom: 247.4 GB
6686
tok/s
Estimated
Weights
0.07 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
0.50 GB
Model details →
#7paraphrase-multilingual-MiniLM-L12-v2
0.118B
other
Commercial OK
Quant: Q4_K_MContext: 128VRAM: 0.6 GBHeadroom: 247.4 GB
6176
tok/s
Estimated
Weights
0.07 GB
KV cache
0.00 GB
Activations
0.00 GB
Runtime
0.50 GB
Model details →
#8Nomic Embed Text v1.5
0.137B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 0.7 GBHeadroom: 247.3 GB
5320
tok/s
Estimated
Weights
0.08 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
0.50 GB
Model details →
#9SmolLM2 135M Instruct
0.135B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 0.7 GBHeadroom: 247.3 GB
5398
tok/s
Estimated
Weights
0.08 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
0.50 GB
Model details →
#10GTE ModernBERT Base
0.149B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 0.7 GBHeadroom: 247.3 GB
4891
tok/s
Estimated
Weights
0.09 GB
KV cache
0.07 GB
Activations
0.01 GB
Runtime
0.50 GB
Model details →
#11Whisper Small
0.244B
other
Commercial OK
Quant: Q4_K_MContext: 30VRAM: 0.7 GBHeadroom: 247.3 GB
2987
tok/s
Estimated
Weights
0.15 GB
KV cache
0.00 GB
Activations
0.01 GB
Runtime
0.50 GB
Model details →
#12Gemma 3 270M
0.27B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 0.8 GBHeadroom: 247.2 GB
2699
tok/s
Estimated
Weights
0.16 GB
KV cache
0.14 GB
Activations
0.02 GB
Runtime
0.50 GB
Model details →

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

Move up an Apple memory tier

~$200–400 over base

On Apple Silicon, more unified memory is the only path forward — VRAM and system RAM are the same pool.

Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Needs ~1024 GB unified memory minimum at smallest quant; you have 248 GB available after OS overhead.

—
Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Needs ~256 GB unified memory minimum at smallest quant; you have 248 GB available after OS overhead.

—
DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Needs ~420 GB unified memory minimum at smallest quant; you have 248 GB available after OS overhead.

—
Mistral Medium 3.5 (675B MoE)
675B
mistral

Needs ~448 GB unified memory minimum at smallest quant; you have 248 GB available after OS overhead.

—
DeepSeek V3 (671B MoE)
671B
deepseek
Commercial OK

Needs ~420 GB unified memory minimum at smallest quant; you have 248 GB available after OS overhead.

—

How to read these numbers

Measured here
Measured here - RunLocalAI ran this exact combo on owner hardware with public evidence.

Source-backed
Source-backed / community - a reproduced public source supports the speed, but it is not labeled as owner-measured.

Extrapolated
Extrapolated - predicted from a measured benchmark on similar-bandwidth hardware.

Estimated
Estimated - formula based on VRAM bandwidth and model architecture; not a benchmark row.

RunLocalAI Will-It-Run Framework →

Want a specific benchmark we don't have? Email Contact support and we'll prioritize it.