Phi-3.5 Vision Instruct on Intel Pentium Gold 8505 NAS (8 GB)

Can the Intel Pentium Gold 8505 NAS (8 GB) run Phi-3.5 Vision Instruct?

Yes, but slowly (far over memory limit)

Slow (far over memory limit). At Q3_K_M it needs about 6.3 GB of 5.2 GB usable, with an estimated speed of 8.7 tok/s.

Best quant: Q3_K_M
Generation speed: 8.7 tok/s
Prompt processing: 24.1 tok/s
First token (1K prompt): 42.5 s
Largest safe context: 5K

Download Phi-3.5 Vision Instruct

Original weights · Hugging Face

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

huggingface.co/microsoft/Phi-3.5-vision-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 31Basic quality (D) · 31 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.: 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 Slowfar over memory limit: How well it runs on the Intel Pentium Gold 8505 NAS (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.	14.4 / 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.	4.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	7.0 / 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	40.3 / 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 Intel Pentium Gold 8505 NAS (8 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	5.9 GB	5.2 GB	11.0 tok/s	Slowfar over memory limit	26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	6.3 GB	5.2 GB	8.7 tok/s	Slowfar over memory limit	31Basic quality (D) · 31 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.	All files (opens in a new tab)
`Q4_K_M`	6.8 GB	5.2 GB	—	Won't run	36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	7.2 GB	5.2 GB	—	Won't run	36Basic quality (D) · 36 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.	All files (opens in a new tab)
`Q6_K`	7.6 GB	5.2 GB	—	Won't run	37Basic quality (D) · 37 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	8.6 GB	5.2 GB	—	Won't run	38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	12.5 GB	5.2 GB	—	Won't run	38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 5/100 (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

38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. Intel Arc B580 Q8_0 · 52.5 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB Q8_0 · 54.2 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER Q8_0 · 75.9 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER F16 · 46.6 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER F16 · 51.1 tok/s · Runs great
38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti F16 · 62.2 tok/s · Runs great

Quick answers

How much memory does Phi-3.5 Vision Instruct need on the Intel Pentium Gold 8505 NAS 8GB?

At Q3_K_M it needs about 6.3 GB. The Intel Pentium Gold 8505 NAS 8GB has 5.2 GB usable.

How fast is Phi-3.5 Vision Instruct on the Intel Pentium Gold 8505 NAS 8GB?

About 8.7 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Phi-3.5 Vision Instruct should I use on the Intel Pentium Gold 8505 NAS 8GB?

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.