Phi-3 Mini 4K Instruct on UP Squared Pro 7000 (8 GB)

Can the UP Squared Pro 7000 (8 GB) run Phi-3 Mini 4K Instruct?

Yes, it runs well (over GPU memory limit)

Runs well (over GPU memory limit). At Q2_K it needs about 4.1 GB of 4.0 GB usable, with an estimated speed of 13.2 tok/s.

Best quant: Q2_K
Generation speed: 13.2 tok/s
Prompt processing: 184 tok/s
First token (1K prompt): 5.6 s
Largest safe context: 3K

Best app to run it on the UP Squared Pro 7000 (8 GB)

On Windows

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Supports Intel Arc through SYCL and Vulkan.

llama-server -hf microsoft/Phi-3-mini-4k-instruct-gguf:Q2_K

LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Supports Intel Arc through SYCL and Vulkan.

llama-server -hf microsoft/Phi-3-mini-4k-instruct-gguf:Q2_K

LM Studio Splits the model between GPU memory and system RAM, which this setup needs.
Ollama Splits the model between GPU memory and system RAM, which this setup needs.

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 Phi-3 Mini 4K Instruct

Recommended for the UP Squared Pro 7000 (8 GB): Q2_K. 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 phi3:3.8b-mini-4k-instruct-q2_K

Quantized files · GGUF

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

huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf (opens in a new tab)

ollama run hf.co/microsoft/Phi-3-mini-4k-instruct-gguf

Original weights · Hugging Face

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

huggingface.co/microsoft/Phi-3-mini-4k-instruct (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, 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 wellover GPU memory limit: How well it runs on the UP Squared Pro 7000 (8 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.	11.3 / 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.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	8.6 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	44.9 / 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 (8 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	4.1 GB	4.0 GB	13.2 tok/s	Runs wellover GPU memory limit	25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.
`Q3_K_M`	4.4 GB	4.0 GB	10.4 tok/s	Slowfar over GPU memory limit	30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking.
`Q4_K_M`	4.9 GB	4.0 GB	8.0 tok/s	Slowfar over GPU memory limit	34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking.
`Q5_K_M`	5.2 GB	4.0 GB	—	Won't run	34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.
`Q6_K`	5.7 GB	4.0 GB	—	Won't run	35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.
`Q8_0`	6.6 GB	4.0 GB	—	Won't run	36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.
`F16`	10.2 GB	4.0 GB	—	Won't run	36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 4/100 (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 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT F16 · 41.5 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Q8_0 · 44.5 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 50.7 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER F16 · 55.5 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti F16 · 67.6 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 F16 · 72.4 tok/s · Runs great

Quick answers

How much memory does Phi-3 Mini 4K Instruct need on the UP Squared Pro 7000 8GB?

At Q2_K it needs about 4.1 GB. The UP Squared Pro 7000 8GB has 4.0 GB usable.

How fast is Phi-3 Mini 4K Instruct on the UP Squared Pro 7000 8GB?

About 13.2 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Phi-3 Mini 4K Instruct should I use on the UP Squared Pro 7000 8GB?

Q2_K. 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.