Can I run Qwen 3.8 2.4T-A95B on an RTX 4080 SUPER (16GB)?
Computed with the open FitLLM engine — accurate per-layer KV-cache modeling, not a naive estimate. Updated 2026-08-24.
Memory breakdown (Q4_K_M, F16 KV, 33K context)
| Model weights | 1394 GB |
| KV cache | 2.9 GB |
| Linear-attention state (fixed — does not grow with context) | 0.5 GB |
| Runtime overhead + reserve | 171 GB |
| Total used | 1568 / 16 GB |
| Short by | 1552 GB |
Max context that fits at Q4_K_M: does not fit.
Every quantization on the RTX 4080 SUPER
| Weight quant | Weights | Fits (KV F16) | Used @32K |
|---|---|---|---|
| Q4_K_M | 1394 GB | ❌ won't fit | 1568 / 16.0 GB |
| Q5_K_M | 1624 GB | ❌ won't fit | 1826 / 16.0 GB |
| Q6_K | 1869 GB | ❌ won't fit | 2100 / 16.0 GB |
| Q8_0 | 2421 GB | ❌ won't fit | 2718 / 16.0 GB |
| FP16 | 4557 GB | ❌ won't fit | 5110 / 16.0 GB |
Lower weight quants free memory at some output-quality cost — Q4 is the common sweet spot; below that quality drops faster.
KV cache is F16 here (llama.cpp default). Drop it to Q8/Q4 (-ctk/-ctv) for more context.
Embed this verdict
Live badge for your README or model card — recomputed by the engine, never stale:
[](https://fitllm.run/can-i-run/qwen-3-8-2-4t-a95b-on-rtx-4080-super)
Or from your terminal (exit 0/1 — works as a pre-download guard):
npx fitllm "Qwen 3.8 2.4T-A95B" --gpu "RTX 4080 SUPER"Why most VRAM calculators get this wrong
Qwen 3.8 2.4T-A95B is a hybrid model: only 23 of its 92 layers use full attention — the rest are linear and keep no growing KV cache. Naive calculators count every layer at full context and badly over-estimate.
What fits on the RTX 4080 SUPER instead
same GPU Models that fit on the RTX 4080 SUPER: Gemma 4 e2b, Gemma 4 e4b, Gemma 4 12b, Llama-3.2-3B-Instruct, Llama-3.1-8B-Instruct, MiniCPM5-1B, Qwen3-0.6B, Qwen3-1.7B, Llama-3.2-1B-Instruct, Gemma-3-1B-it.
same model GPUs that run Qwen 3.8 2.4T-A95B: —.
Reproduce it
Qwen 3.8 2.4T-A95B = 2446.183B (95B active, MoE), 92 layers. The RTX 4080 SUPER has 16GB / 736GB/s. Same math, open source: fitllm-engine. GGUF bpw from llama.cpp.
All numbers are computed by the open-source fitllm-engine (MIT) from official model config.json values — reproduce or audit them yourself. Estimates; real usage varies with runtime (llama.cpp / MLX / Ollama), driver and display. Found a mismatch? Report it. · FitLLM home