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: Out of VRAM (OOM) 126.47 GB / 99.8 GB Usable

Step 3.7 Flash (201B MoE) on AMD Ryzen AI Max+ 395 Mini PC (128GB Unified): VRAM Requirement & Speed Estimate

A single AI Max+ 395 128G (99.8 GB usable VRAM) cannot fully fit Step 3.7 Flash (201B MoE) at Q4_K_M (126.47 GB required). Consider multi-GPU tensor parallelism, a smaller parameter variant, or cloud GPU / API deployment.

Concurrency (Batch):
MoE 201B / A11B·45L (d=4096)·64Q/8KV·Ctx 256K·Text+Image+Video
Runnable Models →
128 GB Unified·256 GB/s·Safe Usable 99.8 GB
Out of VRAM (OOM)126.47 / 99.8 GBOOM
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Out of VRAM (OOM)
126.47/ 99.8 GB usable

Physical 128 GB · Load 126.7%

Theoretical Decode Speed
—tokens/s

Exceeds usable VRAM by 26.63 GB

Max Context at Batch=1
0K/ 256K

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 121.86 GBKV Cache (1×16K): 0.88 GBOverhead: 3.74 GB
Reserves ~22% unified memory for OS
⛔ Cannot Load
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run step-3-7-flash-200b

Insufficient Local VRAM? Ways to Run Step 3.7 Flash (201B MoE)

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 Step 3.7 Flash (201B MoE) on AI Max+ 395 128G

Quantization Total VRAM (16K) Verdict Est. Speed Max Context
FP16 / BF16 412.22 GB Out of VRAM (OOM) — —
FP8 / Q8_0 220.01 GB Out of VRAM (OOM) — —
GGUF Q6_K 170.29 GB Out of VRAM (OOM) — —
GGUF Q5_K_M 148 GB Out of VRAM (OOM) — —
Q4_K_M / AWQ 126.47 GB Out of VRAM (OOM) — —
GGUF IQ4_XS 111.09 GB Out of VRAM (OOM) — —
GGUF Q3_K_M 102.38 GB Out of VRAM (OOM) — —
GGUF Q2_K 82.9 GB Smooth Fit ~35.4 tok/s 256K

💡 Recommended Alternative GPUs & Macs for Step 3.7 Flash (201B MoE)

Frequently Asked Questions

Can AMD Ryzen AI Max+ 395 Mini PC (128GB Unified) run Step 3.7 Flash (201B MoE) locally?

A single AI Max+ 395 128G (99.8 GB usable VRAM) cannot fully fit Step 3.7 Flash (201B MoE) at Q4_K_M (126.47 GB required). Consider multi-GPU tensor parallelism, a smaller parameter variant, or cloud GPU / API deployment.

What is the best quantization for Step 3.7 Flash (201B MoE) on AI Max+ 395 128G?

The highest-quality quantization that fits cleanly on AI Max+ 395 128G is GGUF Q2_K (Extreme Compression), using 82.9 GB VRAM at ~35.4 tokens/s with up to 256K context.

How much VRAM does Step 3.7 Flash (201B MoE) need in full FP16 precision?

In unquantized FP16/BF16 precision (16K context), Step 3.7 Flash (201B MoE) requires 412.22 GB VRAM (402 GB for weights alone). Because it uses a Mixture-of-Experts (MoE) architecture, all 201B parameters must sit in memory, while only 11B active parameters are read per token.