What can Apple Mac Studio (M3 Ultra) run for reasoning?

Build: Mac Studio M3 Ultra 256GB

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

Runs comfortably
215 models

Ranked by fit for reasoning use case + predicted speed. Click a row for VRAM breakdown.

#1Llama 3.1 Nemotron Nano 8B
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 238.3 GB
91
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
0.50 GB
Model details →
#2RefinedNeuro RN TR R1
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 238.3 GB
ollama run RefinedNeuro/RN_TR_R1:latest
91
tok/s
Estimated
Weights
4.90 GB
KV cache
4.00 GB
Activations
0.25 GB
Runtime
0.50 GB
Model details →
#3DeepSeek R1 Distill Llama 8B
8B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 9.4 GBHeadroom: 238.6 GB
91
tok/s
Estimated
Weights
4.70 GB
KV cache
4.00 GB
Activations
0.24 GB
Runtime
0.50 GB
Model details →
#4NVIDIA Nemotron Nano 9B v2 Japanese
9B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 10.3 GBHeadroom: 237.7 GB
81
tok/s
Estimated
Weights
5.00 GB
KV cache
4.50 GB
Activations
0.26 GB
Runtime
0.50 GB
Model details →
#5DeepSeek R1 Distill Qwen 7B
7B
deepseek
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 12.5 GBHeadroom: 235.5 GB
ollama run deepseek-r1:7b
59
tok/s
Estimated
Weights
8.10 GB
KV cache
3.50 GB
Activations
0.41 GB
Runtime
0.50 GB
Model details →
#6DeepSeek V4 Flash (284B MoE)
284B
deepseek
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 206.1 GBHeadroom: 41.9 GB
56
tok/s
Estimated
Weights
162.00 GB
KV cache
35.50 GB
Activations
8.10 GB
Runtime
0.50 GB
Model details →
#7Phi-4 Reasoning 14B
14B
phi
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 16.3 GBHeadroom: 231.7 GB
ollama run phi4-reasoning:14b
52
tok/s
Estimated
Weights
8.40 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
0.50 GB
Model details →
#8DeepSeek R1 Distill Qwen 14B
14B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 16.3 GBHeadroom: 231.7 GB
ollama run deepseek-r1:14b
52
tok/s
Estimated
Weights
8.40 GB
KV cache
7.00 GB
Activations
0.43 GB
Runtime
0.50 GB
Model details →
#9DeepSeek V3 Lite (16B MoE)
16B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 18.5 GBHeadroom: 229.5 GB
304
tok/s
Estimated
Weights
9.50 GB
KV cache
8.00 GB
Activations
0.48 GB
Runtime
0.50 GB
Model details →
#10DeepSeek R1 Distill Mistral 24B
24B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 27.2 GBHeadroom: 220.8 GB
30
tok/s
Estimated
Weights
14.00 GB
KV cache
12.00 GB
Activations
0.71 GB
Runtime
0.50 GB
Model details →
#11InternLM 2.5 7B Chat
7B
internlm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 8.6 GBHeadroom: 239.4 GB
104
tok/s
Estimated
Weights
4.40 GB
KV cache
3.50 GB
Activations
0.23 GB
Runtime
0.50 GB
Model details →
#12Qwen 2.5 Math 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 6.9 GBHeadroom: 241.1 GB
104
tok/s
Estimated
Weights
4.40 GB
KV cache
1.75 GB
Activations
0.22 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.

—
GLM-5.2
753B
glm
Commercial OK

Needs ~528 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.

—

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.