Phi-3.5 Vision Instruct on Intel Celeron J4125 / J4105 NAS (6 GB)
Can the Intel Celeron J4125 / J4105 NAS (6 GB) run Phi-3.5 Vision Instruct?
No, it doesn’t fit
No. Phi-3.5 Vision Instruct needs about 5.8 GB even at Q2_K; the Intel Celeron J4125 / J4105 NAS (6 GB) has 3.5 GB usable.
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)
How it’s rated
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 quality | 3.6 / 45 | |
|---|---|---|
| Memory fit | 0.0 / 25 | |
| Speed | 0.0 / 15 | |
| Memory use | 0.0 / 15 | |
| Match score | 3.6 / 100 |
Every quantization on the Intel Celeron J4125 / J4105 NAS (6 GB)
| Quant | Memory needed | Available | Speed | Runs | Quality | Download |
|---|---|---|---|---|---|---|
Q2_K | 5.8 GB | 3.5 GB | — | Won't run | 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q3_K_M | 6.1 GB | 3.5 GB | — | Won't run | 31Basic quality (D) · 31 of 100: how capable the model is at Q3_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) |
Q4_K_M | 6.6 GB | 3.5 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 | 7.0 GB | 3.5 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 | 7.5 GB | 3.5 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 | 8.5 GB | 3.5 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 | 12.4 GB | 3.5 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.
Hardware that can run 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
-
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
-
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
-
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
-
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
-
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
Models that do run on the Intel Celeron J4125 / J4105 NAS (6 GB)
- 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. MiniCPM5 2B
- 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. LFM3 1.7B
- 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Gemma 4 E2B
- 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Unlimited OCR 2 (3B-A0.6B)
- 48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. LFM3-VL 2B
Quick answers
How much memory does Phi-3.5 Vision Instruct need on the Intel Celeron J4125 / J4105 NAS 6GB?
Even at Q2_K it needs about 5.8 GB; the Intel Celeron J4125 / J4105 NAS 6GB has 3.5 GB usable.
What can the Intel Celeron J4125 / J4105 NAS 6GB run instead?
MiniCPM5 2B, LFM3 1.7B and Gemma 4 E2B run best on it; the page lists more, each with its speed.
What hardware can run Phi-3.5 Vision Instruct?
Arc B580 12GB, RTX 3060 12GB and RTX 4070 SUPER 12GB run it; the page lists more, each with its speed.
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.