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) 23.34 GB / 18.7 GB Usable

Qwen3.5-35B-A3B (MoE) on Apple Mac mini M4 (24GB Unified): VRAM Requirement & Speed Estimate

A single Mac mini M4 24G (18.7 GB usable VRAM) cannot fully fit Qwen3.5-35B-A3B (MoE) at Q4_K_M (23.34 GB required). Consider multi-GPU tensor parallelism, a smaller parameter variant, or cloud GPU / API deployment.

Concurrency (Batch):
MoE 35B / A3B·40L (d=2048)·16Q/2KV·Ctx 256K·Text+Image+Video
Runnable Models →
24 GB Unified·120 GB/s·Safe Usable 18.7 GB
Out of VRAM (OOM)23.34 / 18.7 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)
23.34/ 18.7 GB usable

Physical 24 GB · Load 124.7%

Theoretical Decode Speed
—tokens/s

Exceeds usable VRAM by 4.62 GB

Max Context at Batch=1
0K/ 256K

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 21.22 GBKV Cache (1×16K): 0.4 GBOverhead: 1.72 GB
Reserves ~22% unified memory for OS
⛔ Cannot Load
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run qwen3.5:35b-a3b

Insufficient Local VRAM? Ways to Run Qwen3.5-35B-A3B (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 Qwen3.5-35B-A3B (MoE) on Mac mini M4 24G

Quantization Total VRAM (16K) Verdict Est. Speed Max Context
FP16 / BF16 73.1 GB Out of VRAM (OOM) — —
FP8 / Q8_0 39.63 GB Out of VRAM (OOM) — —
GGUF Q6_K 30.98 GB Out of VRAM (OOM) — —
GGUF Q5_K_M 27.09 GB Out of VRAM (OOM) — —
Q4_K_M / AWQ 23.34 GB Out of VRAM (OOM) — —
GGUF IQ4_XS 20.67 GB Out of VRAM (OOM) — —
GGUF Q3_K_M 19.15 GB Out of VRAM (OOM) — —
GGUF Q2_K 15.76 GB Smooth Fit ~57.3 tok/s 157K

💡 Recommended Alternative GPUs & Macs for Qwen3.5-35B-A3B (MoE)

Frequently Asked Questions

Can Apple Mac mini M4 (24GB Unified) run Qwen3.5-35B-A3B (MoE) locally?

A single Mac mini M4 24G (18.7 GB usable VRAM) cannot fully fit Qwen3.5-35B-A3B (MoE) at Q4_K_M (23.34 GB required). Consider multi-GPU tensor parallelism, a smaller parameter variant, or cloud GPU / API deployment.

What is the best quantization for Qwen3.5-35B-A3B (MoE) on Mac mini M4 24G?

The highest-quality quantization that fits cleanly on Mac mini M4 24G is GGUF Q2_K (Extreme Compression), using 15.76 GB VRAM at ~57.3 tokens/s with up to 157K context.

How much VRAM does Qwen3.5-35B-A3B (MoE) need in full FP16 precision?

In unquantized FP16/BF16 precision (16K context), Qwen3.5-35B-A3B (MoE) requires 73.1 GB VRAM (70 GB for weights alone). Because it uses a Mixture-of-Experts (MoE) architecture, all 35B parameters must sit in memory, while only 3B active parameters are read per token.