Phi-3 Medium 128K Instruct on AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB)

Can the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB) run Phi-3 Medium 128K Instruct?

Yes, it runs well

Runs well. At Q2_K it needs about 16.9 GB of 113 GB usable, with an estimated speed of 10.3 tok/s.

Best quant: Q2_K
Generation speed: 10.3 tok/s
Prompt processing: 31.1 tok/s
First token (1K prompt): 32.9 s
Largest safe context: 128K

Best app to run it on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB)

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run phi3:14b-medium-128k-instruct-q2_K

llama.cpp Usually the first to support new model architectures.
KoboldCpp

How we choose: the files published for this model, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download Phi-3 Medium 128K Instruct

Recommended for the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 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 phi3:14b-medium-128k-instruct-q2_K

Quantized files · GGUF

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

Download the Q2_K file (opens in a new tab)

huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Phi-3-medium-128k-instruct-GGUF:Q2_K

Original weights · Hugging Face

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

huggingface.co/microsoft/Phi-3-medium-128k-instruct (opens in a new tab)

No sign-in needed.

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

How it’s rated

Quality 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (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 well: How well it runs on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 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.	14.5 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); 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.	7.6 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	3.5 / 15
Match score	50.6 / 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 AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (128 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	16.9 GB	113 GB	10.3 tok/s	Runs well	32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	18.1 GB	113 GB	8.1 tok/s	Slow	38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	19.8 GB	113 GB	6.3 tok/s	Slow	43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	21.2 GB	113 GB	5.2 tok/s	Slow	44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	22.7 GB	113 GB	4.4 tok/s	Slow	45Fair quality (C) · 45 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	26.1 GB	113 GB	3.2 tok/s	Slow	46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	39.2 GB	113 GB	1.5 tok/s	Very slow	46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	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

46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 41.9 tok/s · Runs great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 45.1 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q5_K_M · 40.0 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q5_K_M · 48.8 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q5_K_M · 53.5 tok/s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q5_K_M · 65.1 tok/s · Runs great

Quick answers

How much memory does Phi-3 Medium 128K Instruct need on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS 128GB?

At Q2_K it needs about 16.9 GB. The AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS 128GB has 113 GB usable.

How fast is Phi-3 Medium 128K Instruct on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS 128GB?

About 10.3 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Phi-3 Medium 128K Instruct should I use on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS 128GB?

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.