Phi-3 Small 8K Instruct on Intel Celeron J1800 / N3710 / 3865U NAS (32 GB)
Can the Intel Celeron J1800 / N3710 / 3865U NAS (32 GB) run Phi-3 Small 8K Instruct?
Barely: it runs very slowly
Very slow. At Q8_0 it needs about 11.6 GB of 26.2 GB usable, with an estimated speed of 0.2 tok/s.
- Best quant
Q8_0- Generation speed
- 0.2 tok/s
- Prompt processing
- 0.6 tok/s
- First token (1K prompt)
- 1,681.6 s
- Largest safe context
- 8K
Download Phi-3 Small 8K Instruct
Original weights · Hugging Face
Full-precision files from Microsoft, for fine-tuning, vLLM, Transformers.
huggingface.co/microsoft/Phi-3-small-8k-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 | 19.8 / 45 | |
|---|---|---|
| Memory fit | 25.0 / 25 | |
| Speed | 1.1 / 15 | |
| Memory use | 10.2 / 15 | |
| Match score | 56.1 / 100 |
Every quantization on the Intel Celeron J1800 / N3710 / 3865U NAS (32 GB)
| Quant | Memory needed | Available | Speed | Runs | Quality | Download |
|---|---|---|---|---|---|---|
Q2_K | 6.7 GB | 26.2 GB | 0.7 tok/s | Very slow | 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q3_K_M | 7.4 GB | 26.2 GB | 0.6 tok/s | Very slow | 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q4_K_M | 8.3 GB | 26.2 GB | 0.4 tok/s | Very slow | 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q5_K_M | 9.0 GB | 26.2 GB | 0.4 tok/s | Very slow | 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q6_K | 9.8 GB | 26.2 GB | 0.3 tok/s | Very slow | 43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q8_0 | 11.6 GB | 26.2 GB | 0.2 tok/s | Very slow | 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
F16 | 18.6 GB | 26.2 GB | 0.1 tok/s | Very slow | 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (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
-
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4070 SUPER
-
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
AMD Radeon RX 9070 XT
-
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4070 Ti SUPER
-
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4080 SUPER
-
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 5070 Ti
-
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 5080
Quick answers
How much memory does Phi-3 Small 8K Instruct need on the Intel Celeron J1800 / N3710 / 3865U NAS 32GB?
At Q8_0 it needs about 11.6 GB. The Intel Celeron J1800 / N3710 / 3865U NAS 32GB has 26.2 GB usable.
How fast is Phi-3 Small 8K Instruct on the Intel Celeron J1800 / N3710 / 3865U NAS 32GB?
About 0.2 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.
Which quantization of Phi-3 Small 8K Instruct should I use on the Intel Celeron J1800 / N3710 / 3865U NAS 32GB?
Q8_0. 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.