Can I Run Gemma 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
作者： Jakub Rusinowski · 最后更新： 2026年6月3日
Yes — comfortably
Yes, comfortably — Gemma 4 31B at Q8_0 needs about 35.7 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~92.3 GB spare and running at ~5.5 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~5.5 tok/s
See what else this hardware can run →
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
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 |
Gemma 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization
| Quant | Memory needed | Fits 128 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 64.7 GB | ✓ Yes | 128K | ~3 tok/s | 62 GB |
| Q8_0 | 35.7 GB | ✓ Yes | 128K | ~5.5 tok/s | 32.9 GB |
| Q6_K | 28.1 GB | ✓ Yes | 128K | ~7 tok/s | 25.4 GB |
| Q5_K_M | 24.7 GB | ✓ Yes | 128K | ~8 tok/s | 22 GB |
| Q4_K_M | 21.4 GB | ✓ Yes | 128K | ~9.3 tok/s | 18.7 GB |
| Q3_K_M | 15.9 GB | ✓ Yes | 128K | ~12.6 tok/s | 13.2 GB |
| Q2_K | 12.9 GB | ✓ Yes | 128K | ~15.7 tok/s | 10.2 GB |
Which Gemma 4 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Gemma 4 31B | 21.4 GB | ✓ Fits | ~9.3 tok/s |
| Gemma 4 26B-A4B | 17 GB | ✓ Fits | ~59.2 tok/s |
| Gemma 4 12B (Unified) | 8.7 GB | ✓ Fits | ~23.3 tok/s |
| Gemma 4 E4B | 6.8 GB | ✓ Fits | ~32.9 tok/s |
| Gemma 4 E2B | 4.9 GB | ✓ Fits | ~47.8 tok/s |
What to watch out for
- 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 computed from this model's published attention configuration.
FAQ
Can I run Gemma 4 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Yes, comfortably — Gemma 4 31B at Q8_0 needs about 35.7 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~92.3 GB spare and running at ~5.5 tok/s (estimated), with room for about 131,072 tokens of context.
Which quantization of Gemma 4 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?
Q8_0 — it needs about 35.7 GB of the 128 GB available, downloads as roughly 32.9 GB, and runs at an estimated 5.5 tokens/sec with up to 128K of context.
What limits Gemma 4 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 Computers
Other Models on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- GLM-4.7 / GLM-Z1 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- GLM-5 / GLM-5.1 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- GLM-5.3-Flash on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- GPT-OSS on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
- Granite 3.0 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)
Gemma 4 on GPUs
- Gemma 4 on NVIDIA GeForce RTX 5090
- Gemma 4 on NVIDIA GeForce RTX 5080
- Gemma 4 on NVIDIA GeForce RTX 5070 Ti
- Gemma 4 on NVIDIA GeForce RTX 5070