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 23.34 GB / 61.4 GB Usable

Qwen3.5-35B-A3B (MoE) on 华为昇腾 Ascend 910B 64GB (HBM2e): VRAM Requirement & Speed Estimate

Yes. At Q4_K_M 4-bit quantization with a 16K context window, Qwen3.5-35B-A3B (MoE) requires 23.34 GB of VRAM (21.22 GB weights + 0.4 GB KV cache + 1.72 GB overhead), fitting within 昇腾 910B 64G's 61.4 GB usable memory at ~420 tokens/s.

Concurrency (Batch):
MoE 35B / A3B·40L (d=2048)·16Q/2KV·Ctx 256K·Text+Image+Video
Runnable Models →
GPUs
64 GB VRAM·1200 GB/s·Safe Usable 61.4 GB
Smooth Fit23.34 / 61.4 GB~420 tok/s
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Smooth Fit
23.34/ 61.4 GB usable

Physical 64 GB · Load 38%

Theoretical Decode Speed
~420tokens/s

MoE: reads only 1.82 GB active weights/step

Max Context at Batch=1
256K/ 256K

Enable Q8/Q4 KV quantization to scale batch concurrency

Weights: 21.22 GBKV Cache (1×16K): 0.4 GBOverhead: 1.72 GB
🚀 Blazing Fast (Instant CoT)~1.2s for a 500-token response
Reference Launch CLI:
OLLAMA_CONTEXT_LENGTH=16384 ollama run qwen3.5:35b-a3b

昇腾 910B 64G Fits Qwen3.5-35B-A3B (MoE) · Cost & TCO

Approx. $13,200 (~$206/GB VRAM) · 310W TDP

📊 All Quantization Levels for Qwen3.5-35B-A3B (MoE) on 昇腾 910B 64G

Quantization Total VRAM (16K) Verdict Est. Speed Max Context
FP16 / BF16 73.1 GB Partial RAM Offload (Slow) ~48.6 tok/s —
FP8 / Q8_0 39.63 GB Smooth Fit ~255 tok/s 256K
GGUF Q6_K 30.98 GB Smooth Fit ~324.7 tok/s 256K
GGUF Q5_K_M 27.09 GB Smooth Fit ~370.1 tok/s 256K
Q4_K_M / AWQ 23.34 GB Smooth Fit ~420 tok/s 256K
GGUF IQ4_XS 20.67 GB Smooth Fit ~420 tok/s 256K
GGUF Q3_K_M 19.15 GB Smooth Fit ~420 tok/s 256K
GGUF Q2_K 15.76 GB Smooth Fit ~420 tok/s 256K

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

Frequently Asked Questions

Can 华为昇腾 Ascend 910B 64GB (HBM2e) run Qwen3.5-35B-A3B (MoE) locally?

Yes. At Q4_K_M 4-bit quantization with a 16K context window, Qwen3.5-35B-A3B (MoE) requires 23.34 GB of VRAM (21.22 GB weights + 0.4 GB KV cache + 1.72 GB overhead), fitting within 昇腾 910B 64G's 61.4 GB usable memory at ~420 tokens/s.

What is the best quantization for Qwen3.5-35B-A3B (MoE) on 昇腾 910B 64G?

The highest-quality quantization that fits cleanly on 昇腾 910B 64G is FP8 / Q8_0 (99.9% Near-Lossless), using 39.63 GB VRAM at ~255 tokens/s with up to 256K 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.