Source: https://getrigbase.com/models/nex-n2-5-mini/ Last updated: 2026-10-28 [Models](https://getrigbase.com/models/) / Nex N2.5 mini # Best home rig for Nex N2.5 mini Quick answer **How much VRAM does Nex N2.5 mini need?** The weights are about 21.4 GB at Q4_K_M (35B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is 2x RTX 3090 (48 GB) at 187 tok/s. **What is the fastest measured hardware for Nex N2.5 mini?** 2x RTX 3090: 187 tok/s generation (vLLM TP2, 1 stream, Int4-Int8Mix), from https://github.com/tonyd2wild/Nex-N2.5-mini-Int4-Int8Mix-2x-RTX-3090. Last updated: 28 Oct 2026 Current model 35B total · 3B active 2 measured results fastest plain decode: 187 tok/s [model info ↗](https://huggingface.co/nex-agi/Nex-N2.5-mini) [Will it fit my GPU?](https://getrigbase.com/can-it-run/) [Best value GPU per euro →](https://getrigbase.com/guides/best-value-gpu-local-llm-europe/) Real, measured generation speeds for Nex N2.5 mini on home hardware, fastest first. Different quants/engines aren't directly comparable. | Build | Quant | Engine | tok/s | Prompt processing (tok/s) | Cost | Source | |---|---|---|---|---|---|---| | [2x RTX 3090: Nex N2.5 mini Int4-Int8Mix on vLLM TP2, 187 tok/s prose (Tech2wild)](https://getrigbase.com/builds/tony-2x-rtx-3090-nex-n2-5-mini-int4-int8mix-2x-rtx-3090/) | Int4-Int8Mix | vLLM TP2, 1 stream | **187** | – | | [github.com ↗](https://github.com/tonyd2wild/Nex-N2.5-mini-Int4-Int8Mix-2x-RTX-3090) | | [2x RTX 3090: Nex N2.5 mini Int4-Int8Mix on vLLM TP2, 187 tok/s prose (Tech2wild)](https://getrigbase.com/builds/tony-2x-rtx-3090-nex-n2-5-mini-int4-int8mix-2x-rtx-3090/) | Int4-Int8Mix | vLLM TP2, 1 stream | **186** | – | | [github.com ↗](https://github.com/tonyd2wild/Nex-N2.5-mini-Int4-Int8Mix-2x-RTX-3090) | Prompt processing = prefill speed reported by the source, @ prompt length. * est. TTFT @8k is calculated from measured prefill, not measured. [Why it matters](https://getrigbase.com/can-it-run/#prefill). Ad · this space is available **Sponsor this spot: reach people building local AI rigs.** One clearly-labeled slot per page, no tracking scripts. [Sponsor this spot →](https://getrigbase.com/advertise/#inquiry) **Rent before you buy:** try this model on a cloud GPU for a few dollars first: [Runpod](https://runpod.io?ref=77qcpl2c) (referral link; sign up with Google to get the new-user bonus) ## Memory math: how much VRAM / RAM does Nex N2.5 mini need? Nex N2.5 mini has **35B parameters**, about **3B active** per token ([source](https://huggingface.co/nex-agi/Nex-N2.5-mini): nex-agi Nex-N2.5-mini 35B-A3B agentic fine-tune with vision tower). Weight size = parameters × bits-per-weight ÷ 8, before context (KV cache) and runtime overhead. | Format | Bits/weight | Weights | Smallest common memory size that holds the weights alone | |---|---|---|---| | Q8_0 | 8.50 | 37.2 GB | 48 GB | | Q6_K | 6.56 | 28.7 GB | 32 GB | | Q5_K_M | 5.70 | 25.0 GB | 32 GB | | Q4_K_M | 4.89 | **21.4 GB** | 24 GB | | Q3_K_M | 4.00 | 17.5 GB | 24 GB | | Q2_K | 3.16 | 13.8 GB | 16 GB | Bits-per-weight for GGUF quants are llama.cpp's own figures ([llama.cpp quantize README](https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md)). "As measured" rows apply the source's stated bits-per-weight to the parameter count; real files differ slightly because some layers stay at higher precision. Try other combinations in the [VRAM calculator](https://getrigbase.com/can-it-run/). **Why it can still run on smaller GPUs:** it is a mixture-of-experts model, so only about 3B of its 35B parameters are used for each generated token. Runtimes such as llama.cpp (--n-cpu-moe), ExLlamaV3 or Project Maya can keep most expert weights in system RAM and only the shared layers and hot experts in VRAM. Then you need **VRAM + system RAM ≥ weights**, and speed is limited mainly by RAM bandwidth. ## FAQ ### How much VRAM does Nex N2.5 mini need? The weights are about 21.4 GB at Q4_K_M (35B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is 2x RTX 3090 (48 GB) at 187 tok/s. ### What is the fastest measured hardware for Nex N2.5 mini? 2x RTX 3090: 187 tok/s generation (vLLM TP2, 1 stream, Int4-Int8Mix), from https://github.com/tonyd2wild/Nex-N2.5-mini-Int4-Int8Mix-2x-RTX-3090. ### Which GPUs have measured results for Nex N2.5 mini? 2x RTX 3090. **Can it run on…** [2x RTX 3090](https://getrigbase.com/can-i-run/nex-n2-5-mini-on-2x-rtx-3090/) Related: [what GPU do you need for 2026 models](https://getrigbase.com/guides/what-gpu-for-qwen3-6-gemma-4-gpt-oss/) · [all builds](https://getrigbase.com/builds/)