Best Local LLMs for 128GB RAM
Ranked open-weight models that run well on a 128GB 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 ~128GB
12 picksEstimates assume a representative Apple-Silicon machine with 128GB 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
Qwen3.5 122B-A10B Instruct
Best for frontier-level reasoning, complex tasks. Strong fit for 128 GB RAM with balanced speed and quality.
$ollama run qwen3.5:122b-a10b- Fit
- Runs wellB · 34
- Best for
- Frontier-level reasoning, Complex tasks
- Perf
- est. 102 tok/s, typical error 10% · first token ~0.2s
- 02
Nemotron 3 Super 120B-A12B
This model may feel memory-heavy on 128 GB RAM, but it is still listed for balanced speed and quality.
$ollama run nemotron-3-super:120b- Fit
- Runs wellC · 20
- Best for
- Agentic workflows, Long context, Reasoning
- Perf
- est. 61 tok/s, typical error 10% · first token ~0.3s
- 03
Nemotron 3 Super 120B-A12B (IQ4_XS)
Best for agentic workflows, long context, reasoning. Strong fit for 128 GB RAM with balanced speed and quality.
$ollama run nemotron-3-super-120b-q4xs- Fit
- Runs wellB · 41
- Best for
- Agentic workflows, Long context, Reasoning
- Perf
- est. 79 tok/s, typical error 10% · first token ~0.3s
- 04
Qwen3.8-Flash-Next (IQ4_XS)
This model may feel memory-heavy on 128 GB RAM, but it is still listed for balanced speed and quality.
$ollama run qwen3.8-flash-next-q4xs- Fit
- Runs wellC · 14
- Best for
- Agentic coding, Reasoning, Multimodal
- Perf
- est. 127 tok/s, typical error 10% · first token ~0.2s
- 05
Ling-3.0-flash
Best for agentic coding, long context, reasoning. Strong fit for 128 GB RAM with balanced speed and quality.
$ollama run ling-3.0-flash- Fit
- Runs wellB · 28
- Best for
- Agentic coding, Long context, Reasoning
- Perf
- est. 152 tok/s, typical error 10% · first token ~0.1s
- 06
Laguna S 2.1
This model may feel memory-heavy on 128 GB RAM, but it is still listed for balanced speed and quality.
$ollama run laguna-s-2.1:q4_K_M- Fit
- Runs wellC · 12
- Best for
- Agentic coding, Long-horizon tasks
- Perf
- est. 85 tok/s, typical error 10% · first token ~0.2s
- 07
Ling-3.0-flash (IQ4_XS)
Best for agentic coding, long context, reasoning. Strong fit for 128 GB RAM with balanced speed and quality.
$ollama run ling-3.0-flash-q4xs- Fit
- Runs wellB · 37
- Best for
- Agentic coding, Long context, Reasoning
- Perf
- est. 165 tok/s, typical error 10% · first token ~0.1s
- 08
GPT-OSS 120B
Best for reasoning, coding, agents. Strong fit for 128 GB RAM with balanced speed and quality.
$ollama run gpt-oss:120b- Fit
- Runs wellB · 40
- Best for
- Reasoning, Coding, Agents
- Perf
- est. 146 tok/s, typical error 10% · first token ~0.1s
- 09
Kolibri 1
Best for reasoning, german, long context. Strong fit for 128 GB RAM with balanced speed and quality.
$ollama run kolibri-1-q4- Fit
- Runs wellB · 54
- Best for
- Reasoning, German, Long context
- Perf
- est. 181 tok/s, typical error 10% · first token ~0.1s
- 10
Qwen3.8-Flash-Next (Q3)
This model may feel memory-heavy on 128 GB RAM, but it is still listed for balanced speed and quality.
$ollama run qwen3.8-flash-next-q3- Fit
- Runs wellC · 17
- Best for
- Agentic coding, Reasoning, Multimodal
- Perf
- est. 130 tok/s, typical error 10% · first token ~0.2s
- 11
Kolibri 1 (IQ4_XS)
Best for reasoning, german, long context. Strong fit for 128 GB RAM with balanced speed and quality.
$ollama run kolibri-1-q4xs- Fit
- Lots of roomA · 60
- Best for
- Reasoning, German, Long context
- Perf
- est. 196 tok/s, typical error 10% · first token ~0.1s
- 12
Qwen3.6 35B-A3B (Q8)
Best for reasoning, coding, agents. Strong fit for 128 GB RAM with balanced speed and quality.
$ollama run qwen3.6:35b-a3b-q8_0- Fit
- Lots of roomA · 64
- Best for
- Reasoning, Coding, Agents
- Perf
- est. 160 tok/s, typical error 10% · first token ~0.1s
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.