HARDWARE FIT CHECK • Qwen 3.6 35B-A3B MoE + NVIDIA GeForce RTX 5090 (32GB GDDR7)24.1 GB / 32 GB VRAM

Can I Run Qwen 3.6 35B-A3B MoE on NVIDIA GeForce RTX 5090 (32GB GDDR7)?

Full VRAM footprint analysis, tokens/sec generation benchmark, and copy-paste Ollama & vLLM runtime commands for running Qwen 3.6 35B-A3B MoE (35B) on NVIDIA GeForce RTX 5090 (32GB GDDR7) (32 GB).

✅ Runs 100% in GPU VRAM (Optimal Headroom)24.1 GB (75%)~553 t/s

Model & Target Hardware

interactive

Model35B MoE

Ultra-Fast 100+ tok/s Coding & Local RAG on 24GB GPUs

Target Hardware32GB • 1792 GB/s

▼ Fine-Tune Precision (Q4_K_M, 32K ctx, Q8_0 KV)quant / context

Qwen 3.6 35B-A3B MoE on NVIDIA GeForce RTX 5090 (32GB GDDR7)

✓ Fits Comfortably in VRAM

✓ FITS IN VRAM

Required VRAM

24.1 GB

75% of hardware capacity (32 GB)

Est. Decode Speed

~553 tok/s

3B active params @ 1792 GB/s

Available Headroom

+7.9 GB

Safe for OS display & full context

Memory Allocation & Headroom

24.1 GB allocated of 32 GB capacity

75% utilized

Weights: 21 GB

KV: (32K): 1.61 GB

Overhead: 1.49 GB

Free Headroom: +7.9 GB

⚡ Architecture & Throughput Transparency: Single-user decode speed (~553 tok/s) is memory-bandwidth bound at batch size = 1 on NVIDIA GeForce RTX 5090 (32GB GDDR7) (1792 GB/s). Prompt prefill / TTFT (~8,019 tok/s) is compute-bound and utilizes GPU Tensor cores. Actual latency varies with FlashAttention-2 and runtime engine (Ollama/vLLM/llama.cpp).

OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 ollama run qwen3.6:35b-a3b

Cloud Instance Options for Qwen 3.6 35B-A3B MoE

On-Demand

Deploy this model on an on-demand cloud GPU without local hardware constraints or power usage:

RunPod Cloud GPUsBest 1-Click Ollama & vLLM

$0.34/hr (RTX 4070 Ti) – $2.39/hr (H100)

Launch 1-Click GPU Pod → →

Vast.ai GPU MarketplaceCheapest Dual RTX 3090 / 4090

$0.18/hr (RTX 3060) – $0.55/hr (RTX 4090)

Rent Spot GPU → →

Lambda GPU CloudEnterprise 8x H100 Clusters

$1.99/hr (GH200 / H100)

Check H100 Availability → →

Quantization Precision Matrix

32K ctx • KV: Q8_0

Quantization	Weights	KV Cache	Total VRAM	Est. Speed	Fit Status
FP1616 bpw	70 GB	1.61 GB	74.81 GB (234%)	0 t/s	OOM
Q8_08.5 bpw	37.1 GB	1.61 GB	40.76 GB (127%)	~75 t/s	PARTIAL
Q6_K6.56 bpw	28.7 GB	1.61 GB	32.06 GB (100%)	~94 t/s	PARTIAL
Q5_K_M5.68 bpw	24.85 GB	1.61 GB	28.08 GB (88%)	~481 t/s	FITS
Q4_K_M4.8 bpw	21 GB	1.61 GB	24.1 GB (75%)	~553 t/s	FITS
FP44.25 bpw	18.55 GB	1.61 GB	21.56 GB (67%)	~612 t/s	FITS
IQ3_XS3.3 bpw	14.35 GB	1.61 GB	17.21 GB (54%)	~746 t/s	FITS