Best Local LLMs for 72GB RAM

Ranked open-weight models that run well on a 72GB machine, with estimated speed and the exact ollama command for each.

Try: RTX 4090, MacBook Pro M4, 16GB, iPhone 17 Pro

Best local models for ~72GB

12 picks

Estimates assume a representative Apple-Silicon machine with 72GB unified memory. Tok/s are ModelFit estimates, not measured benchmarks. Run the wizard for figures tuned to your exact chip.

01

Qwen3.6 35B-A3B (Q8)

Qwen / 35B / Q8_0 / ~38.7 GB

Best for: Reasoning, Coding, Agents·Perf: ~72.4 tok/s · first token ~1.4s

Runs well

Best for reasoning, coding, agents. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.6:35b-a3b-q8_0
02

Qwen3.5 35B-A3B Instruct (Q8)

Qwen / 35B / Q8_0 / ~38.7 GB

Best for: Reasoning, Coding, Agent scenarios·Perf: ~72.4 tok/s · first token ~1.4s

Runs well

Best for reasoning, coding, agent scenarios. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.5:35b-a3b-q8_0
03

Qwen3.6 35B-A3B

Qwen / 35B / Q4_K_M / ~22 GB

Best for: Reasoning, Coding, Agents·Perf: ~116.7 tok/s · first token ~1.3s

Perfect fit

Best for reasoning, coding, agents. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.6:35b-a3b
04

Qwen3.5 35B-A3B Instruct

Qwen / 35B / Q4_K_M / ~20 GB

Best for: Reasoning, Coding, Agent scenarios·Perf: ~116.7 tok/s · first token ~1.3s

Perfect fit

Best for reasoning, coding, agent scenarios. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.5:35b-a3b
05

Gemma 4 26B-A4B (Q8)

Gemma / 26B / Q8_0 / ~28.1 GB

Best for: Chat, Coding, Multimodal·Perf: ~72.7 tok/s · first token ~0.6s

Runs well

Best for chat, coding, multimodal. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run gemma4:26b-a4b-it-q8_0
06

Qwen3.6 27B (Q8)

Qwen / 27B / Q8_0 / ~30 GB

Best for: Coding, Quality, Long context·Perf: ~30.3 tok/s · first token ~0.8s

Runs well

Best for coding, quality, long context. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.6:27b-q8_0
07

Qwen3.6 27B

Qwen / 27B / Q4_K_M / ~18 GB

Best for: Coding, Quality, Long context·Perf: ~48.8 tok/s · first token ~0.7s

Perfect fit

Best for coding, quality, long context. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.6:27b
08

Qwen3-Next 80B-A3B

Qwen / 80B / Q4_K_M / ~50.4 GB

Best for: Chat, Coding, Long Context·Perf: ~68.6 tok/s · first token ~1.4s

Runs well

This model may feel memory-heavy on 72 GB RAM, but it is still listed for balanced speed and quality.

ollama
$ollama run qwen3-next:80b
09

Qwen3 30B

Qwen / 30B / Q4_K_M / ~22 GB

Best for: Quality, Coding·Perf: ~125.1 tok/s · first token ~1.3s

Perfect fit

Best for quality, coding. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3:30b
10

Llama 3.3 70B Instruct

Llama / 70B / Q4_K_M / ~42 GB

Best for: Quality, Coding·Perf: ~20.7 tok/s · first token ~1.7s

Runs well

This model may feel memory-heavy on 72 GB RAM, but it is still listed for balanced speed and quality.

ollama
$ollama run llama3.3:70b-instruct-q4_K_M
11

Gemma 4 31B

Gemma / 31B / Q4_K_M / ~20 GB

Best for: Quality, Coding, Multimodal·Perf: ~43.1 tok/s · first token ~1.5s

Perfect fit

Best for quality, coding, multimodal. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run gemma4:31b
12

Mixtral 8x7B Instruct

Mistral / 46.7B / Q4_K_M / ~30 GB

Best for: Coding, Quality·Perf: ~53 tok/s · first token ~1.4s

Runs well

Best for coding, quality. Strong fit for 72 GB RAM with balanced speed and quality.

ollama
$ollama run mixtral:8x7b

Browse by RAM tier

8 GB16 GB24 GB32 GB48 GB64 GB96 GB128 GB

Want an exact recommendation?

The wizard tunes picks and speed estimates to your exact device, chip, and RAM.

Open ModelFit Wizard Browse all devices