Can I Run Qwen 2.5 Family on 128 GB system RAM?

Superseded model. Qwen 2.5 Family has been superseded by Qwen 3. This page is kept for reference; the newer family is a better starting point. View Qwen 3 →

Written by Jakub Rusinowski · Last updated November 12, 2024

Technically yes, but not recommended

It loads, but it is not worth running — Qwen 2.5 72B Instruct at Q8_0 fits in 128 GB system RAM's 102.4 GB, yet the memory bandwidth limits it to ~0.9 tok/s (estimated), well below usable interactive speed.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~0.9 tok/s

128 GB system RAM — what it gives a model

Usable memory for models102.4 GB
Memory bandwidth90 GB/s

Qwen 2.5 Family on 128 GB system RAM: memory by quantization

QuantMemory neededFits 102.4 GB?Max contextEst. speedDownload
F16147.5 GB✗ No144 GB
Q8_080 GB✓ Yes64K~0.9 tok/s76.5 GB
Q6_K62.5 GB✓ Yes64K~1.1 tok/s59 GB
Q5_K_M54.5 GB✓ Yes128K~1.3 tok/s51 GB
Q4_K_M47 GB✓ Yes128K~1.5 tok/s43.5 GB
Q3_K_M34.2 GB✓ Yes128K~2.1 tok/s30.7 GB
Q2_K27.2 GB✓ Yes128K~2.7 tok/s23.7 GB

Which Qwen 2.5 Family sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Qwen 2.5 72B Instruct47 GB✓ Fits~1.5 tok/s
Qwen 2.5 Coder 32B22.3 GB✓ Fits~3.3 tok/s
Qwen 2.5 14B Instruct10.9 GB✓ Fits~7.1 tok/s
Qwen 2.5 7B Instruct5.9 GB✓ Fits~13.5 tok/s

What to watch out for

Recommended setup

llama.cpp (CPU build) or Ollama — both run without a GPU

How these numbers are calculated

FAQ

Can I run Qwen 2.5 Family on 128 GB system RAM?

It loads, but it is not worth running — Qwen 2.5 72B Instruct at Q8_0 fits in 128 GB system RAM's 102.4 GB, yet the memory bandwidth limits it to ~0.9 tok/s (estimated), well below usable interactive speed.

Which quantization of Qwen 2.5 Family should I use on 128 GB system RAM?

Q8_0 — it needs about 80 GB of the 102.4 GB available, downloads as roughly 76.5 GB, and runs at an estimated 0.9 tokens/sec with up to 64K of context.

What limits Qwen 2.5 Family on 128 GB system RAM?

Memory bandwidth. The model fits, but at 89.6 GB/s it can only be read fast enough for roughly 0.9 tokens/sec.

Which runtime should I use?

llama.cpp (CPU build) or Ollama — both run without a GPU

Other RAM Capacities

Other Models on 128 GB system RAM

Qwen 2.5 Family on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Qwen 2.5 Family model page | Check your hardware