Can I Run Qwen 3.8 235B-A22B MoE on NVIDIA GeForce RTX 5080 (16GB GDDR7)?
Full VRAM footprint analysis, tokens/sec generation benchmark, and copy-paste Ollama & vLLM runtime commands for running Qwen 3.8 235B-A22B MoE (235B) on NVIDIA GeForce RTX 5080 (16GB GDDR7) (16 GB).
✕ Out of Memory — Exceeds VRAM Capacity
Local Hardware Configurations & Pricing
Out of VRAM: High-Capacity Hardware Upgrades2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM)
Best price-to-VRAM homelab rig for Llama 3.3 70B Q4_K_M & Qwen 2.5 Coder 32B Q8_0
NVIDIA GeForce RTX 5080 (16GB GDDR7)
Blazing fast 8B–14B coding models with FP4/Q6_K precision
Apple Mac Mini M4 Pro (64GB Unified Memory)
Silent 65W desktop running 32B–70B models with large KV context
Apple Mac Studio M4 Max (128GB Unified Memory)
Running Mistral Large 2 123B & Llama 3.3 70B Q8_0 locally with 128K context
Out of VRAM? Don't downgrade model quality.
Out of VRAMSpin up an on-demand cloud GPU instance in 60 seconds with pre-installed Ollama and vLLM. (Qwen 3.8 235B-A22B MoE @ 149.84 GB VRAM)
Quantization Precision Matrix
32K ctx • KV: Q8_0| Quantization | Weights | KV Cache | Total VRAM | Est. Speed | Fit Status |
|---|---|---|---|---|---|
| FP1616 bpw | 470 GB | 3.15 GB | 490.35 GB (999%) | 0 t/s | OOM |
| Q8_08.5 bpw | 249.1 GB | 3.15 GB | 261.72 GB (999%) | 0 t/s | OOM |
| Q6_K6.56 bpw | 192.7 GB | 3.15 GB | 203.34 GB (999%) | 0 t/s | OOM |
| Q5_K_M5.68 bpw | 166.85 GB | 3.15 GB | 176.59 GB (999%) | 0 t/s | OOM |
| Q4_K_M4.8 bpw | 141 GB | 3.15 GB | 149.84 GB (937%) | 0 t/s | OOM |
| FP44.25 bpw | 124.55 GB | 3.15 GB | 132.81 GB (830%) | 0 t/s | OOM |
| IQ3_XS3.3 bpw | 96.35 GB | 3.15 GB | 103.62 GB (648%) | 0 t/s | OOM |
Export Full Architecture & Infrastructure Spec
Download an instant Markdown architecture spec with exact memory math, hardware benchmarks, and runtime CLI flags.
Frequently Asked Questions: Qwen 3.8 235B-A22B MoE on NVIDIA GeForce RTX 5080 (16GB GDDR7)
How much VRAM does Qwen 3.8 235B-A22B MoE need on NVIDIA GeForce RTX 5080 (16GB GDDR7)?
At standard 4-bit quantization (Q4_K_M) with 32K context, Qwen 3.8 235B-A22B MoE requires 149.84 GB of total VRAM (weights + KV cache + CUDA runtime overhead).
What inference speed will Qwen 3.8 235B-A22B MoE achieve on NVIDIA GeForce RTX 5080 (16GB GDDR7)?
Based on NVIDIA GeForce RTX 5080 (16GB GDDR7)'s 960 GB/s memory bandwidth, expected decode speed is approximately 0 tokens per second.
Can I expand context beyond 32K tokens?
Each additional 32K tokens of context requires additional KV cache memory. For longer context windows, consider 8-bit or 4-bit KV cache quantization.