Nex N2.5 Mini — Hardware Requirements & GPU Compatibility
ChatFunctions
Nex N2.5 Mini is a 35.1B-parameter open language model from nex-agi. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 21.45 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 12 GB (IQ2_XS · 64K)Best on 24 GB (Q4_K_M · ~171 tok/s · 128K)Macs from 16 GB (IQ2_M · ~57 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Nex N2.5 Mini
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/abenzerps/Nex-N2.5-mini-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 2.5 GB free · 16K context
Download: Nex-N2.5-mini-Q4_K_M.gguf21.17 GBabenzerps
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX PRO 4500 (32 GB) (10 GB headroom) · Q4_K_M
- Generation speed
- ~159 tok/s
- generation speed
- Cost per 1M output tokens
- $0.59
- per 1M output tokens
How Much VRAM Does Nex N2.5 Mini Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.3 GB | 15.6 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~209 tok/s | |
| 15.7 GB | 16 GB | 3-bit small — 3-bit small quantization | Fits: 256K context · ~205 tok/s | |
| 17.5 GB | 17.8 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~194 tok/s | |
| 17.9 GB | 18.2 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 256K context · ~191 tok/s | |
| 21.4 GB | 21.7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~171 tok/s | |
| 25.4 GB | 25.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 25.5 GB | |
| 29.4 GB | 29.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 29.4 GB | |
| 35.5 GB | 35.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 35.6 GB |
Selected Q4_K_M
4-bit medium quantization21.5GBat 16K context
- Weights
- 21.1 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 2.5 GB free · ~171 tok/s
≥50 tok/s needs ≥206 GB/s · RTX 5090 ~236, RTX 3090 Ti ~171
Or .
Which Hardware Can Run Nex N2.5 Mini?
Q4_K_M · 21.4 GBNex N2.5 Mini (Q4_K_M) requires 21.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. Using the full 262K context window can add up to 2.6 GB, bringing total usage to 24.1 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090. 100 devices with unified memory can run Nex N2.5 Mini, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit Q4_0 (18.0 GB)
1 GPU
RX 7900 XT~82Simulate output on RX 7900 XT32–40 GB
fits · 10.5 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~236Simulate output on RTX 5090M5 Max36 GB~65Simulate output on Mac Studio M5 Max (36 GB)M532 GB~33Simulate output on MacBook Air 13" M5 (32 GB)Orin~50Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~32Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.6 35B A3BAlibaba | 106.8 | 22 GB | ~151 | same size |
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| Ornith 1.5 35B A3Bornith-ai | — | 22 GB | ~151 | same size |
| Agents A1InternScience | — | 21.5 GB | ~171 | same size |
| Intern S2 PreviewInternLM | — | 73.2 GB | —needs > 24 GB | same size |
| EXAONE 4.5 33BLGAI-EXAONE | — | 23.9 GB | ~33 | same size |
Fine-tunes & variants(1)
Specifications
- Publisher
- nex-agi
- Parameters
- 35.1B
- Active parameters
- 3.9B per token
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-09-08
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Nex N2.5 Mini need?
Nex N2.5 Mini requires 21.4 GB of VRAM at Q4_K_M, or 70.6 GB at BF16. Full 262K context adds up to 2.6 GB (24.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 35.1B × 4.8 bits ÷ 8 = 21.1 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 2.9 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Nex N2.5 Mini?
Yes, at Q4_K_M (21.4 GB) or lower. Higher quantizations like Q5_K_S (24.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Nex N2.5 Mini?
For Nex N2.5 Mini, Q4_K_M (21.4 GB) offers the best balance of quality and VRAM usage. Q5_K_S (24.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 10.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Nex N2.5 Mini on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Nex N2.5 Mini, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 21.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run Nex N2.5 Mini locally?
Yes — Nex N2.5 Mini can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Nex N2.5 Mini?
At Q4_K_M, Nex N2.5 Mini can reach ~118 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~171 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 2.4 GB active ÷ (8000 × 0.65) = 0.46 ms, plus 40 layers × 0.055 ms = 2.20 ms, so 1000 ÷ 2.66 ms = ~376 tok/s
Estimated speed at Q4_K_M (21.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Nex N2.5 Mini?
At Q4_K_M, the download is about 21.06 GB. The full-precision BF16 version is 70.21 GB. The smallest option (IQ2_XXS) is 9.65 GB.
Which GPUs can run Nex N2.5 Mini?
7 consumer GPUs can run Nex N2.5 Mini at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
Which devices can run Nex N2.5 Mini?
100 devices with unified memory can run Nex N2.5 Mini at Q4_K_M (21.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.