01
Qwen3-Next 80B-A3B
Qwen / 80B / Q4_K_M / ~50.4 GB
Best for: Chat, Coding, Long Context·Perf: ~44.6 tok/s · first token ~1.5s
Best for chat, coding, long context. Strong fit for 96 GB RAM with balanced speed and quality.
$ollama run qwen3-next:80b
Best Local LLMs for 96GB RAM
Ranked open-weight models that run well on a 96GB 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 ~96GB
12 picksEstimates assume a representative Apple-Silicon machine with 96GB unified memory. Tok/s are ModelFit estimates, not measured benchmarks. Run the wizard for figures tuned to your exact chip.
Runs well
02
Qwen3.6 35B-A3B (Q8)
Qwen / 35B / Q8_0 / ~38.7 GB
Best for: Reasoning, Coding, Agents·Perf: ~36.9 tok/s · first token ~1.5s
Best for reasoning, coding, agents. Strong fit for 96 GB RAM with balanced speed and quality.
$ollama run qwen3.6:35b-a3b-q8_0
03
Qwen3.5 35B-A3B Instruct (Q8)
Qwen / 35B / Q8_0 / ~38.7 GB
Best for: Reasoning, Coding, Agent scenarios·Perf: ~36.9 tok/s · first token ~1.5s
Best for reasoning, coding, agent scenarios. Strong fit for 96 GB RAM with balanced speed and quality.
$ollama run qwen3.5:35b-a3b-q8_0
04
Nemotron 3.5 Lightning 30B-A3B
Nemotron / 30B / Q4_K_M / ~23.7 GB
Best for: Agentic, Coding, Long context·Perf: ~72.8 tok/s · first token ~1.4s
Best for agentic, coding, long context. Strong fit for 96 GB RAM with balanced speed and quality.
$ollama run nemotron-3.5-lightning:30b
05
GPT-OSS 120B
GPT-OSS / 117B / MXFP4 / ~65.4 GB
Best for: Reasoning, Coding, Agents·Perf: ~29.8 tok/s · first token ~1.6s
This model may feel memory-heavy on 96 GB RAM, but it is still listed for balanced speed and quality.
$ollama run gpt-oss:120b
06
Qwen3.5 122B-A10B Instruct
Qwen / 122B / Q4_K_M / ~72 GB
Best for: Frontier-level reasoning, Complex tasks·Perf: ~19 tok/s · first token ~1.8s
This model may feel memory-heavy on 96 GB RAM, but it is still listed for balanced speed and quality.
$ollama run qwen3.5:122b-a10b
07
Llama 4 Scout
Llama / 109B / Q4_K_M / ~67 GB
Best for: Long context, Quality, Multimodal·Perf: ~16.1 tok/s · first token ~1.9s
This model may feel memory-heavy on 96 GB RAM, but it is still listed for balanced speed and quality.
$ollama run llama4:scout
08
Llama 3.3 70B Instruct
Llama / 70B / Q4_K_M / ~42 GB
Best for: Quality, Coding·Perf: ~9.9 tok/s · first token ~2.3s
Best for quality, coding. Strong fit for 96 GB RAM with balanced speed and quality.
$ollama run llama3.3:70b-instruct-q4_K_M
09
Gemma 4 26B-A4B (Q8)
Gemma / 26B / Q8_0 / ~28.1 GB
Best for: Chat, Coding, Multimodal·Perf: ~37.1 tok/s · first token ~0.7s
Best for chat, coding, multimodal. Strong fit for 96 GB RAM with balanced speed and quality.
$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: ~67.4 tok/s · first token ~1.4s
Best for reasoning, coding, agents. Strong fit for 96 GB RAM with balanced speed and quality.
$ollama run qwen3.6:35b-a3b
11
Qwen3.8 27B (Q8)
Qwen / 27B / Q8_0 / ~27.1 GB
Best for: Coding, Agent, Vision, Long context·Perf: ~14 tok/s · first token ~1.2s
Best for coding, agent, vision, long context. Strong fit for 96 GB RAM with balanced speed and quality.
$ollama run qwen3.8:27b-q8_0
12
Qwen3.5 35B-A3B Instruct
Qwen / 35B / Q4_K_M / ~20 GB
Best for: Reasoning, Coding, Agent scenarios·Perf: ~67.4 tok/s · first token ~1.4s
Best for reasoning, coding, agent scenarios. Strong fit for 96 GB RAM with balanced speed and quality.
$ollama run qwen3.5:35b-a3b
Want an exact recommendation?
The wizard tunes picks and speed estimates to your exact device, chip, and RAM.