llmrun
orcarouter

Nex N2.5 Mini Uncensored — Hardware Requirements & GPU Compatibility

ChatVisionFunctionsReasoning

Nex N2.5 Mini Uncensored is a 35.1B-parameter open language model from orcarouter. At Q4_K_M it needs about 23.17 GB of VRAM — see which GPUs and Macs can run it below.

35.1B params · denseApache 2.01.6K downloads9 likes
Based on Nex N2.5 Mini
C

Usable on a 24 GB GPU

Runs on24 GB Q4_K_M · ~28 tok/s · 4KMacs from24 GB Q2_K · ~13 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Nex N2.5 Mini Uncensored

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

vLLM
one command · needs vLLM installed
$vllm serve orcarouter/Nex-N2.5-mini-Uncensored --max-model-len 16384

vLLM repo with its own quantisation

Download: Weights on Hugging Face

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on A100 40GB (12 GB headroom) · Q4_K_M

Generation speed
~44 tok/s
generation speed
Cost per 1M output tokens
$3.88
per 1M output tokens
Deployon Vast.aiBest valuefrom $0.61/hr (opens in new tab)
Compare GPUs →
or

How Much VRAM Does Nex N2.5 Mini Uncensored Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
16.4 GB24.7 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 16K context · ~40 tok/s
18.8 GB27.2 GB3-bit medium — 3-bit medium quantizationFits: 16K context · ~35 tok/s
23.2 GB31.5 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 4K context · ~28 tok/s
27.5 GB35.8 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffDoes not fit: needs 31.4 GB
31.9 GB40.2 GB6-bit, very good — 6-bit quantization, very good qualityDoes not fit: needs 35.7 GB
38.6 GB46.9 GB8-bit, near-lossless — 8-bit quantization, near-losslessDoes not fit: needs 42.5 GB
77.2 GB85.6 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingDoes not fit: needs 81.1 GB
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

27.1GBat 16K context

Weights
22.3 GB
KV cache
4.4 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · fits up to 4K context · ~28 tok/s

≥50 tok/s needs ≥1.78 TB/s · RTX 5090 ~50

Or .

Which Hardware Can Run Nex N2.5 Mini Uncensored?

Q4_K_M · 23.2 GB

Nex N2.5 Mini Uncensored (Q4_K_M) requires 23.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 31+ GB is recommended. 7 GPUs can run it, including NVIDIA GeForce RTX 5090. 100 devices with unified memory can run Nex N2.5 Mini Uncensored, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Max (36 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8–16 GB · RTX 4060, RTX 3060 12GB, RTX 5060 Ti 16GBDoesn't fit — smallest quant needs 20.3 GB8 GB tier →12 GB tier →16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 27.1 GB · ~28 tok/s · 4Ktight24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 27.1 GB · ~4 tok/s · 16KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 27.1 GB · ~17 tok/s · 32KMacs →

Alternatives to Nex N2.5 Mini Uncensored

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Qwen3.6 35B A3BAlibaba106.822 GB~151same size
MiniCPM V 4.7 35B A3BOpenBMB—22.1 GB~169same size
Ornith 1.5 35B A3Bornith-ai—22 GB~151same size
Agents A1InternScience—21.5 GB~171same size
Intern S2 PreviewInternLM—73.2 GB—needs > 24 GBsame size
EXAONE 4.5 33BLGAI-EXAONE—23.9 GB~33same size

Specifications

Publisher
orcarouter
Parameters
35.1B
Release Date
2026-09-10
License
Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does Nex N2.5 Mini Uncensored need?

Nex N2.5 Mini Uncensored requires 23.2 GB of VRAM at Q4_K_M, or 77.2 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 35.1B × 4.8 bits ÷ 8 = 21.1 GB

KV Cache + Overhead ≈ 2.1 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.

VRAM usage by quantization

23.2 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Nex N2.5 Mini Uncensored?

Yes, at Q4_K_M (23.2 GB) or lower. Higher quantizations like Q5_K_M (27.5 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Nex N2.5 Mini Uncensored?

For Nex N2.5 Mini Uncensored, Q4_K_M (23.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (27.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 16.4 GB.

VRAM requirement by quantization

Q2_K
16.4 GB
Q4_K_M ★
23.2 GB
Q5_K_M
27.5 GB
Q6_K
31.9 GB
Q8_0
38.6 GB
BF16
77.2 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Nex N2.5 Mini Uncensored on a Mac?

Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Nex N2.5 Mini Uncensored, the smallest at Q2_K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 23.2 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).

Can I run Nex N2.5 Mini Uncensored locally?

Yes — Nex N2.5 Mini Uncensored can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Nex N2.5 Mini Uncensored?

At Q4_K_M, Nex N2.5 Mini Uncensored can reach ~207 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~28 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 23.2 × 0.65 = ~224 tok/s

Estimated speed at Q4_K_M (23.2 GB)

~224 tok/s
~28 tok/s
~224 tok/s
~207 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Nex N2.5 Mini Uncensored?

At Q4_K_M, the download is about 21.06 GB. The full-precision BF16 version is 70.21 GB. The smallest option (Q2_K) is 14.92 GB.

Which GPUs can run Nex N2.5 Mini Uncensored?

7 consumer GPUs can run Nex N2.5 Mini Uncensored at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.

Which devices can run Nex N2.5 Mini Uncensored?

100 devices with unified memory can run Nex N2.5 Mini Uncensored at Q4_K_M (23.2 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.