Can I Run GLM-5.3-Flash on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Written by Jakub Rusinowski · Last updated September 11, 2026
Yes
Yes — GLM-5.3-Flash 320B-A18B at Q2_K needs about 110 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB) (~18 GB spare), at ~23.1 tok/s (estimated), with room for about 32,768 tokens of context.
Confidence: medium · Recommended quantization: Q2_K · Estimated speed: ~23.1 tok/s
or compare on Vast.ai
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Framework Desktop (Ryzen AI Max+ 395, 128 GB) — what it gives a model
| Usable memory for models | 128 GB |
| Memory bandwidth | 256 GB/s |
| Form factor | Mini PC |
| Operating system | Windows or Linux |
| Memory upgradeable | No — soldered |
GLM-5.3-Flash on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|
| F16 | 644.8 GB | ✗ No | — | — | 640 GB |
| Q8_0 | 344.8 GB | ✗ No | — | — | 340 GB |
| Q6_K | 267.2 GB | ✗ No | — | — | 262.4 GB |
| Q5_K_M | 231.6 GB | ✗ No | — | — | 226.8 GB |
| Q4_K_M | 198 GB | ✗ No | — | — | 193.2 GB |
| Q3_K_M | 141.2 GB | ✗ No | — | — | 136.4 GB |
| Q2_K | 110 GB | ✓ Yes | 32K | ~23.1 tok/s | 105.2 GB |
What to watch out for
- Q2_K is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
- 1 larger variant of GLM-5.3-Flash does not fit and would need CPU offload or different hardware.
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
- Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.
Framework Desktop 128 GB limitations
- Memory is soldered LPDDR5X — unusually for Framework, this is the one component that cannot be upgraded.
- ROCm/Vulkan support for Strix Halo is younger than CUDA; check your runtime supports it before buying.
Recommended setup
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 128 GB unified memory at 256 GB/s, shared between CPU and GPU.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run GLM-5.3-Flash on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Yes — GLM-5.3-Flash 320B-A18B at Q2_K needs about 110 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB) (~18 GB spare), at ~23.1 tok/s (estimated), with room for about 32,768 tokens of context.
Which quantization of GLM-5.3-Flash should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Q2_K — it needs about 110 GB of the 128 GB available, downloads as roughly 105.2 GB, and runs at an estimated 23.1 tokens/sec with up to 32K of context.
What limits GLM-5.3-Flash on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Models on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
GLM-5.3-Flash on GPUs
What This Model Is Good At
Model & Tools
← Can I Run It? | GLM-5.3-Flash model page | Check your hardware