Best Local LLMs for 64GB RAM
Ranked open-weight models that run well on a 64GB machine, with estimated speed and the exact ollama command for each.
Try: Qwen3 8B, RTX 4090, MacBook Pro M4, 16GB, iPhone 17 Pro
Best local models for ~64GB
12 picksEstimates assume a representative Apple-Silicon machine with 64GB unified memory. Tok/s are ModelFit estimates, not measured benchmarks; typical error is the median gap to measured runs on hardware the model was not fitted on (how the estimates work). Run the wizard for figures tuned to your exact chip.
- 01
Qwen3.6 35B-A3B (Q8)
This model may feel memory-heavy on 64 GB RAM, but it is still listed for balanced speed and quality.
$ollama run qwen3.6:35b-a3b-q8_0- Fit
- Runs wellC · 19
- Best for
- Reasoning, Coding, Agents
- Perf
- est. 99 tok/s, typical error 10% · first token ~0.4s
- 02
Nemotron 3.5 Lightning 30B-A3B
Best for agentic, coding, long context. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run nemotron-3.5-lightning:30b- Fit
- Runs wellB · 47
- Best for
- Agentic, Coding, Long context
- Perf
- est. 99 tok/s, typical error 10% · first token ~0.5s
- 03
Gemma 4 26B-A4B (Q8)
Best for chat, coding, multimodal. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run gemma4:26b-a4b-it-q8_0- Fit
- Runs wellB · 41
- Best for
- Chat, Coding, Multimodal
- Perf
- est. 76 tok/s, typical error 10% · first token ~0.5s
- 04
Kolibri 1 (IQ4_XS)
This model may feel memory-heavy on 64 GB RAM, but it is still listed for balanced speed and quality.
$ollama run kolibri-1-q4xs- Fit
- Runs wellC · 9
- Best for
- Reasoning, German, Long context
- Perf
- est. 121 tok/s, typical error 10% · first token ~0.5s
- 05
Qwen3.6 35B-A3B
Best for reasoning, coding, agents. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run qwen3.6:35b-a3b- Fit
- Runs wellB · 54
- Best for
- Reasoning, Coding, Agents
- Perf
- est. 139 tok/s, typical error 10% · first token ~0.4s
- 06
Qwen3.8 27B (Q8)
Best for coding, agent, vision, long context. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run qwen3.8:27b-q8_0- Fit
- Runs wellB · 44
- Best for
- Coding, Agent, Vision, Long context
- Perf
- est. 21 tok/s, typical error 10% · first token ~3.4s
- 07
Qwen3.8 27B
Best for coding, agent, vision, long context. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run qwen3.8:27b- Fit
- Lots of roomA · 66
- Best for
- Coding, Agent, Vision, Long context
- Perf
- est. 34 tok/s, typical error 10% · first token ~3.3s
- 08
Gemma 4 26B-A4B
Best for chat, coding, multimodal. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run gemma4:26b- Fit
- Lots of roomA · 67
- Best for
- Chat, Coding, Multimodal
- Perf
- est. 103 tok/s, typical error 10% · first token ~0.4s
- 09
NVIDIA Nemotron Cascade 2 30B-A3B
Best for reasoning, math, agentic tasks. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run nemotron-cascade-2:30b- Fit
- Runs wellB · 50
- Best for
- Reasoning, Math, Agentic tasks
- Perf
- est. 102 tok/s, typical error 10% · first token ~0.7s
- 10
Gemma 4 31B (Q8)
Best for quality, coding, multimodal. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run gemma4:31b-it-q8_0- Fit
- Runs wellB · 36
- Best for
- Quality, Coding, Multimodal
- Perf
- est. 17 tok/s, typical error 10% · first token ~4.2s
- 11
Nemotron 3.5 Lightning 30B-A3B (IQ4_XS)
Best for agentic, coding, long context. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run nemotron-3.5-lightning-30b-q4xs- Fit
- Lots of roomA · 61
- Best for
- Agentic, Coding, Long context
- Perf
- est. 120 tok/s, typical error 10% · first token ~0.5s
- 12
Gemma 4 31B
Best for quality, coding, multimodal. Strong fit for 64 GB RAM with balanced speed and quality.
$ollama run gemma4:31b- Fit
- Runs wellB · 58
- Best for
- Quality, Coding, Multimodal
- Perf
- est. 28 tok/s, typical error 10% · first token ~4.0s
Get told when a better model fits your MacBook Air M5 16 GB
Get one email when a new open-weight model is a better fit for this machine.
For: MacBook Air M5 16 GB
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Browse by RAM tier
Want an exact recommendation?
The wizard tunes picks and speed estimates to your exact device, chip, and RAM.