Best Local LLMs for 192GB RAM

Ranked open-weight models that run well on a 192GB 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 ~192GB

12 picks

Estimates assume a representative Apple-Silicon machine with 192GB unified memory. Tok/s are ModelFit estimates, not measured benchmarks. Run the wizard for figures tuned to your exact chip.

01

Qwen3 235B A22B

Qwen / 235B / Q4_K_M / ~130 GB

Best for: Quality, Reasoning·Perf: ~9.2 tok/s · first token ~2.3s

Runs well

This model may feel memory-heavy on 192 GB RAM, but it is still listed for balanced speed and quality.

ollama
$ollama run qwen3:235b-a22b-q4_K_M
02

Qwen3-Next 80B-A3B (Q8)

Qwen / 80B / Q8_0 / ~84.8 GB

Best for: Chat, Coding, Long Context·Perf: ~23.4 tok/s · first token ~1.7s

Runs well

Best for chat, coding, long context. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3-next:80b-a3b-instruct-q8_0
03

GPT-OSS 120B

GPT-OSS / 117B / MXFP4 / ~65.4 GB

Best for: Reasoning, Coding, Agents·Perf: ~28.6 tok/s · first token ~1.6s

Perfect fit

Best for reasoning, coding, agents. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run gpt-oss:120b
04

Qwen3-Next 80B-A3B

Qwen / 80B / Q4_K_M / ~50.4 GB

Best for: Chat, Coding, Long Context·Perf: ~42.7 tok/s · first token ~1.5s

Perfect fit

Best for chat, coding, long context. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3-next:80b
05

Qwen3.5 122B-A10B Instruct

Qwen / 122B / Q4_K_M / ~72 GB

Best for: Frontier-level reasoning, Complex tasks·Perf: ~18.9 tok/s · first token ~1.8s

Runs well

Best for frontier-level reasoning, complex tasks. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.5:122b-a10b
06

Llama 4 Scout

Llama / 109B / Q4_K_M / ~67 GB

Best for: Long context, Quality, Multimodal·Perf: ~15.4 tok/s · first token ~1.9s

Runs well

Best for long context, quality, multimodal. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run llama4:scout
07

Qwen3.6 35B-A3B (Q8)

Qwen / 35B / Q8_0 / ~38.7 GB

Best for: Reasoning, Coding, Agents·Perf: ~35.3 tok/s · first token ~1.5s

Perfect fit

Best for reasoning, coding, agents. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.6:35b-a3b-q8_0
08

Qwen3.5 35B-A3B Instruct (Q8)

Qwen / 35B / Q8_0 / ~38.7 GB

Best for: Reasoning, Coding, Agent scenarios·Perf: ~35.3 tok/s · first token ~1.5s

Perfect fit

Best for reasoning, coding, agent scenarios. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.5:35b-a3b-q8_0
09

Gemma 4 26B-A4B (Q8)

Gemma / 26B / Q8_0 / ~28.1 GB

Best for: Chat, Coding, Multimodal·Perf: ~35.5 tok/s · first token ~0.7s

Perfect fit

Best for chat, coding, multimodal. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run gemma4:26b-a4b-it-q8_0
10

Qwen3.6 35B-A3B

Qwen / 35B / Q4_K_M / ~22 GB

Best for: Reasoning, Coding, Agents·Perf: ~64.6 tok/s · first token ~1.4s

Perfect fit

Best for reasoning, coding, agents. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.6:35b-a3b
11

Qwen3.5 35B-A3B Instruct

Qwen / 35B / Q4_K_M / ~20 GB

Best for: Reasoning, Coding, Agent scenarios·Perf: ~64.6 tok/s · first token ~1.4s

Perfect fit

Best for reasoning, coding, agent scenarios. Strong fit for 192 GB RAM with balanced speed and quality.

ollama
$ollama run qwen3.5:35b-a3b
12

Qwen3.6 27B (Q8)

Qwen / 27B / Q8_0 / ~30 GB

Best for: Coding, Quality, Long context·Perf: ~13.4 tok/s · first token ~1.2s

Perfect fit

Best for coding, quality, long context. Strong fit for 192 GB RAM with balanced speed and quality.

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

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