Can Nex N2.6 run on the RTX 3080 10GB?
Not fully in VRAM. Even at 2-bit with 8K context, Nex N2.6 needs about 118 GB, more than the 9.5 GB usable on the RTX 3080 10GB. It can still run with offload (slower): Q2_K with part of the model in system RAM, about 6.6–13 tokens/sec (estimate). Details and command.
Runs with offload (slower)
Runs with offload 2-bit (Q2_K) at 8K context: all attention layers plus the experts of 1 of 43 MoE layers on the RTX 3080 10GB (about 6.3 GB), and the experts of the other 42 layers in system RAM (about 111 GB). Needs a PC with at least 128 GB of system RAM. Estimated speed: 6.6–13 tokens/sec (slow but usable), versus a bandwidth ceiling of ~106 tok/s if it fit fully in VRAM.
llama-server -hf bartowski/Nex-N2.6-GGUF:Q2_K -c 8192 -ngl 999 --n-cpu-moe 44
Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, raise --n-cpu-moe by 1-2; if VRAM is left over, lower it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.
+ 1.1 GB with image input. The figures on this page are for text only. Sending images also loads the vision projector (mmproj) file. Calculator with image input on.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 118 GB No | 118 GB No | 118 GB No | 119 GB No | — |
| 3-bit (Q3_K_M) • | 145 GB No | 145 GB No | 145 GB No | 147 GB No | — |
| 4-bit (Q4_K_M) • | 188 GB No | 188 GB No | 188 GB No | 189 GB No | — |
| 5-bit (Q5_K_M) • | 228 GB No | 228 GB No | 228 GB No | 229 GB No | — |
| 6-bit (Q6_K) • | 262 GB No | 263 GB No | 263 GB No | 264 GB No | — |
| 8-bit (Q8_0) • | 319 GB No | 319 GB No | 319 GB No | 320 GB No | — |
| 16-bit (F16/BF16) | 599 GB No | 599 GB No | 600 GB No | 601 GB No | — |
• real GGUF file size from bartowski/Nex-N2.6-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.
Hardware that does fit it
H200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB
What fits instead
- No listed GPU with a list price runs Nex N2.6 fully in memory. The smallest listed hardware that does is the H200 (141 GB).
- Largest popular model that fits the RTX 3080 10GB: KORMo Web 11B (11B) at Q4_K_M, about 8.3 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
Nex N2.6 on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (nex-agi/Nex-N2.6), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.