What can you run with 128GB of RAM?

With 128GB RAM you can run 19 of the 30 open-source models we track — up to about 199B parameters at Q4 quantization. The most popular that fits is Qwen3.5-9B, needing 6.8 GB and generating around ~62 tok/s on typical hardware of this size.

Typical machines: Mac Studio M3 Ultra · Threadripper workstation · Multi-GPU server. After the operating system takes its share, about 133 GB is free for a model.

Having the memory is not the same as having the speed

128GB RAM decides whether a model loads. How fast it answers is decided by memory bandwidth — how quickly your machine can read the model, which it must do once for every word it writes. Machines with 128GB RAM span 90–819 GB/s, so the fastest is about 9.1× quicker than the slowest with identical capacity. The table quotes a Mac M4 Max; pick yours below to see the difference. Why bandwidth and not the processor →

90 GB/sDesktop or laptop — DDR5-5600· 5,600 MT/s × 128-bit dual channel ÷ 8 = 89.6 GB/s
128 GB/sEnthusiast desktop — DDR5-8000· 8,000 MT/s × 128-bit dual channel ÷ 8 = 128 GB/s
546 GB/sMacBook Pro or Mac Studio — M4 Max· Apple published specification for the M4 Max: 546 GB/s
819 GB/sMac Studio — M3 Ultra· Apple published specification for the M3 Ultra: 819 GB/s

Models that run on 128GB RAM in 2026

ModelSizeMemoryEst. speedFeels like
Qwen3.5-9BAlibaba / Qwen9.7B6.8 GBRuns well~62 tok/sFast
gpt-oss-20bOpenAI · MoE22B13 GBRuns well~153 tok/s4.3B activeFast
Qwen3.5-4BAlibaba / Qwen4.7B3.8 GBRuns well~129 tok/sFast
gpt-oss-120bOpenAI · MoE120B66 GBRuns well~28 tok/s24B activeFast
Qwen3.5-0.8BAlibaba / Qwen873M1.3 GBRuns well~666 tok/sFast
Qwen3.5-27BAlibaba / Qwen28B19 GBRuns well~21 tok/sComfortable
Qwen3.5-35B-A3BAlibaba / Qwen · MoE36B25 GBRuns well~81 tok/s7.2B activeFast
Qwen3.5-2BAlibaba / Qwen2.3B2.0 GBRuns well~277 tok/sFast
GLM-4.7-FlashZhipu AI31B22 GBRuns well~19 tok/sComfortable
Qwen3.5-122B-A10BAlibaba / Qwen · MoE125B82 GBRuns well~23 tok/s25B activeComfortable
Olmo-3-7B-InstructAi27.3B7.2 GBRuns well~79 tok/sFast
Qwen3-Next-80B-A3B-InstructAlibaba / Qwen · MoE81B52 GBRuns well~37 tok/s16B activeFast
GLM-4.6V-FlashZhipu AI10B7.0 GBRuns well~58 tok/sFast
ERNIE-4.5-VL-28B-A3B-PTBaidu AI · MoE29B20 GBRuns well~20 tok/sComfortable
Mistral-Small-4-119B-2603Mistral AI119B79 GBRuns well~4.8 tok/sSlow
Step-3.5-FlashStepFun199B85 GBRuns well~4.9 tok/sSlow
Olmo-3.1-32B-InstructAi232B23 GBRuns well~18 tok/sComfortable
ERNIE-4.5-21B-A3B-PTBaidu AI · MoE22B15 GBRuns well~26 tok/sFast
ERNIE-4.5-0.3B-PTBaidu AI361M853 MBRuns well~1475 tok/sFast

All figures at Q4_K_M quantization, 4K context. “Memory” includes the model, its context cache and runtime overhead. Speed is calculated, not benchmarked: 546 GB/s × 0.65 ÷ bytes read per token, assuming a Mac M4 Max. Scale it by your own machine's bandwidth from the list above. Mixture-of-experts models read only their active parameters per token, which is why some large ones outrun smaller dense models.

Image generators that also fit

These make pictures rather than text. Their memory use scales with the resolution you generate at, not conversation length, so treat these figures as a floor rather than a ceiling.

What you'd need more memory for

The next models up, and what they ask for.

MiniMax-M2.5needs 143 GB
MiniMax-M2.7needs 144 GB
Qwen3.5-397B-A17Bneeds 244 GB

Other hardware

Verified against HuggingFace on 2026-08-01New to this? Start here →Runs on a laptop and up · last 12 months only