Nemotron 3 Nano 4B on UP Squared Pro 7000 (16 GB)

Can the UP Squared Pro 7000 (16 GB) run Nemotron 3 Nano 4B?

Yes, it runs well

Runs well. At Q3_K_M it needs about 3.3 GB of 8.0 GB usable, with an estimated speed of 11.7 tok/s.

Best quant: Q3_K_M
Generation speed: 11.7 tok/s
Prompt processing: 177 tok/s
First token (1K prompt): 5.8 s
Largest safe context: 256K

Best app to run it on the UP Squared Pro 7000 (16 GB)

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

Supports Intel Arc through SYCL and Vulkan.
Usually the first to support new model architectures.

llama-server -hf unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF:Q3_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama Intel GPU support here is experimental (Vulkan).

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Supports Intel Arc through SYCL and Vulkan.
Usually the first to support new model architectures.

llama-server -hf unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF:Q3_K_M

LM Studio Point-and-click: search, download and chat in one window.
Ollama Intel GPU support here is experimental (Vulkan).

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Nemotron 3 Nano 4B

Recommended for the UP Squared Pro 7000 (16 GB): Q3_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run nemotron-3-nano:4b

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q3_K_M file (opens in a new tab)

huggingface.co/unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF:Q3_K_M

Original weights · Hugging Face

Full-precision files from NVIDIA, for fine-tuning, vLLM, Transformers.

huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from NVIDIA. The weights themselves download from Hugging Face.

github.com/NVIDIA-NeMo/Nemotron (opens in a new tab)

NVIDIA’s Nemotron repo with recipes for the whole family.

git clone https://github.com/NVIDIA-NeMo/Nemotron

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q3_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well: How well it runs on the UP Squared Pro 7000 (16 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	18.9 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	8.1 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	9.6 / 15
Match score	61.6 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the UP Squared Pro 7000 (16 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	3.0 GB	8.0 GB	14.9 tok/s	Runs well	35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	3.3 GB	8.0 GB	11.7 tok/s	Runs well	42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	3.8 GB	8.0 GB	9.1 tok/s	Slow	47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	4.2 GB	8.0 GB	7.5 tok/s	Slow	48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	4.6 GB	8.0 GB	6.3 tok/s	Slow	49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	5.6 GB	8.0 GB	4.6 tok/s	Slow	50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	9.3 GB	8.0 GB	1.8 tok/s	Very slowfar over GPU memory limit	50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q8_0 · 42.8 tok/s · Runs great
50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 48.7 tok/s · Runs great
50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER F16 · 53.4 tok/s · Runs great
50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti F16 · 65.0 tok/s · Runs great
50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 F16 · 69.6 tok/s · Runs great
50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q8_0 · 54.8 tok/s · Runs great

Quick answers

How much memory does Nemotron 3 Nano 4B need on the UP Squared Pro 7000 16GB?

At Q3_K_M it needs about 3.3 GB. The UP Squared Pro 7000 16GB has 8.0 GB usable.

How fast is Nemotron 3 Nano 4B on the UP Squared Pro 7000 16GB?

About 11.7 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Nemotron 3 Nano 4B should I use on the UP Squared Pro 7000 16GB?

Q3_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.