ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Q4_K_M: Smooth Fit 22.47 GB / 99.8 GB Usable

Gemma-4-31B-IT on AMD Ryzen AI Max+ 395 Mini PC (128GB Unified): VRAM Requirement & Speed Estimate

Yes. At Q4_K_M 4-bit quantization with a 16K context window, Gemma-4-31B-IT requires 22.47 GB of VRAM (18.61 GB weights + 2.18 GB KV cache + 1.67 GB overhead), fitting within AI Max+ 395 128G's 99.8 GB usable memory at ~8.6 tokens/s.

Concurrency (Batch):
Dense 30.7B·60L (d=5376)·32Q/4KV·Ctx 256K·Text+Image+Video
Runnable Models →
128 GB Unified·256 GB/s·Safe Usable 99.8 GB
Smooth Fit22.47 / 99.8 GB~8.6 tok/s
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Smooth Fit
22.47/ 99.8 GB usable

Physical 128 GB · Load 22.5%

Theoretical Decode Speed
~8.6tokens/s

Actual speed varies ~±25% by runtime

Max Context at Batch=1
256K/ 256K

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 18.61 GBKV Cache (1×16K): 2.18 GBOverhead: 1.67 GB
Reserves ~22% unified memory for OS
🚶 Readable Pace~58.1s for a 500-token response
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run gemma4:31b

Insufficient Local VRAM? Ways to Run Gemma-4-31B-IT

Rent an hourly high-VRAM cloud GPU pod, or check the 12-month Buy vs Cloud vs API break-even curve.

📊 All Quantization Levels for Gemma-4-31B-IT on AI Max+ 395 128G

Quantization Total VRAM (16K) Verdict Est. Speed Max Context
FP16 / BF16 66.11 GB Smooth Fit ~2.7 tok/s 256K
FP8 / Q8_0 36.75 GB Smooth Fit ~5 tok/s 256K
GGUF Q6_K 29.16 GB Smooth Fit ~6.4 tok/s 256K
GGUF Q5_K_M 25.75 GB Smooth Fit ~7.4 tok/s 256K
Q4_K_M / AWQ 22.47 GB Smooth Fit ~8.6 tok/s 256K
GGUF IQ4_XS 20.12 GB Smooth Fit ~9.7 tok/s 256K
GGUF Q3_K_M 18.79 GB Smooth Fit ~10.5 tok/s 256K
GGUF Q2_K 15.81 GB Smooth Fit ~12.8 tok/s 256K

💡 Recommended Alternative GPUs & Macs for Gemma-4-31B-IT

Frequently Asked Questions

Can AMD Ryzen AI Max+ 395 Mini PC (128GB Unified) run Gemma-4-31B-IT locally?

Yes. At Q4_K_M 4-bit quantization with a 16K context window, Gemma-4-31B-IT requires 22.47 GB of VRAM (18.61 GB weights + 2.18 GB KV cache + 1.67 GB overhead), fitting within AI Max+ 395 128G's 99.8 GB usable memory at ~8.6 tokens/s.

What is the best quantization for Gemma-4-31B-IT on AI Max+ 395 128G?

The highest-quality quantization that fits cleanly on AI Max+ 395 128G is FP16 / BF16 (Lossless Full Precision), using 66.11 GB VRAM at ~2.7 tokens/s with up to 256K context.

How much VRAM does Gemma-4-31B-IT need in full FP16 precision?

In unquantized FP16/BF16 precision (16K context), Gemma-4-31B-IT requires 66.11 GB VRAM (61.4 GB for weights alone).