Skip to content

Phi 3 Mini 128K Instruct VRAM requirements

How much VRAM Phi 3 Mini 128K Instruct needs
4-bit weights: 2.2 GBWith 8K context: 5.8 GBWith 32K context: 14.8 GB8-bit, 8K context: 7.4 GB
Parameters
3.8B
Longest context
128K
Released
Apr 2024
License
MIT
Strongest at
Not rated

How much VRAM Phi 3 Mini 128K Instruct needs

Memory Phi 3 Mini 128K Instruct needs at each precision and context length
PrecisionWeightsWith 8KWith 32KWith 128K
16-bit7.1 GB10.7 GB19.7 GB55.7 GB
8-bit3.8 GB7.4 GB16.4 GB52.4 GB
6-bit2.9 GB6.5 GB15.5 GB51.5 GB
5-bit2.5 GB6.1 GB15.1 GB51.1 GB
4-bit2.2 GB5.8 GB14.8 GB50.8 GB
3-bit1.7 GB5.3 GB14.3 GB50.3 GB
2-bit1.3 GB4.9 GB13.9 GB49.9 GB
1.6-bit752 MB4.3 GB13.3 GB49.3 GB

One conversation, 16-bit context cache, runtime overhead included.

GPUs and Macs that run Phi 3 Mini 128K Instruct

The best way Phi 3 Mini 128K Instruct runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 4060Too bigPDF: Phi 3 Mini 128K Instruct on RTX 4060 report
RTX 5060Too bigPDF: Phi 3 Mini 128K Instruct on RTX 5060 report
RTX 3070Too bigPDF: Phi 3 Mini 128K Instruct on RTX 3070 report
RTX 3080 10 GB5-bit16K168 tok/s0.3 sPDF: Phi 3 Mini 128K Instruct on RTX 3080 10 GB report
RTX 3060 12 GB8-bit16K60 tok/s0.6 sPDF: Phi 3 Mini 128K Instruct on RTX 3060 12 GB report
Arc B5808-bit16K52 tok/s0.4 sPDF: Phi 3 Mini 128K Instruct on Arc B580 report
RTX 40708-bit16K82 tok/s0.3 sPDF: Phi 3 Mini 128K Instruct on RTX 4070 report
RTX 4070 Super8-bit16K82 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on RTX 4070 Super report
RTX 50708-bit16K107 tok/s0.3 sPDF: Phi 3 Mini 128K Instruct on RTX 5070 report
RTX 4060 Ti 16 GB8-bit28K49 tok/s0.4 sPDF: Phi 3 Mini 128K Instruct on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GB8-bit28K74 tok/s0.3 sPDF: Phi 3 Mini 128K Instruct on RTX 5060 Ti 16 GB report
Arc A770 16 GB8-bit28K62 tok/s0.4 sPDF: Phi 3 Mini 128K Instruct on Arc A770 16 GB report
Radeon RX 9070 XT8-bit28K84 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on Radeon RX 9070 XT report
RTX 4070 Ti Super8-bit28K107 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on RTX 4070 Ti Super report
RTX 4080 Super8-bit28K116 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on RTX 4080 Super report
RTX 5070 Ti8-bit28K138 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on RTX 5070 Ti report
RTX 50808-bit28K146 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on RTX 5080 report
Radeon RX 7900 XTX8-bit48K118 tok/s0.4 sPDF: Phi 3 Mini 128K Instruct on Radeon RX 7900 XTX report
RTX 30908-bit48K143 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on RTX 3090 report
RTX 40908-bit48K152 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on RTX 4090 report
Radeon AI PRO R97008-bit64K84 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on Radeon AI PRO R9700 report
RTX 50908-bit64K243 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on RTX 5090 report
2× RTX 30908-bit104K143 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 2× RTX 3090 report
2× RTX 40908-bit104K152 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GB8-bit104K194 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 Ada8-bit104K146 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on RTX 6000 Ada report
L40S8-bit104K133 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on L40S report
2× RTX 50908-bit128K243 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 2× RTX 5090 report
4× RTX 30908-bit128K143 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 4× RTX 3090 report
RTX PRO 6000 Blackwell8-bit128K243 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on RTX PRO 6000 Blackwell report
Mac mini M4 16 GB6-bit16K30 tok/s5.2 sPDF: Phi 3 Mini 128K Instruct on Mac mini M4 16 GB report
Mac mini M4 24 GB8-bit28K23 tok/s5.2 sPDF: Phi 3 Mini 128K Instruct on Mac mini M4 24 GB report
Mac mini M4 32 GB8-bit40K23 tok/s5.2 sPDF: Phi 3 Mini 128K Instruct on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GB8-bit28K49 tok/s2.6 sPDF: Phi 3 Mini 128K Instruct on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GB8-bit80K49 tok/s2.6 sPDF: Phi 3 Mini 128K Instruct on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GB8-bit104K49 tok/s2.6 sPDF: Phi 3 Mini 128K Instruct on Mac mini M4 Pro 64 GB report
M4 Max 128 GB8-bit128K82 tok/s1.3 sPDF: Phi 3 Mini 128K Instruct on M4 Max 128 GB report
M5 Max 128 GB8-bit128K90 tok/s0.4 sPDF: Phi 3 Mini 128K Instruct on M5 Max 128 GB report
M3 Ultra 96 GB8-bit128K100 tok/s0.7 sPDF: Phi 3 Mini 128K Instruct on M3 Ultra 96 GB report
M3 Ultra 256 GB8-bit128K100 tok/s0.7 sPDF: Phi 3 Mini 128K Instruct on M3 Ultra 256 GB report
M3 Ultra 512 GB8-bit128K100 tok/s0.7 sPDF: Phi 3 Mini 128K Instruct on M3 Ultra 512 GB report
M5 Ultra 512 GB8-bit128K131 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GB8-bit104K37 tok/s0.8 sPDF: Phi 3 Mini 128K Instruct on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GB8-bit128K37 tok/s0.8 sPDF: Phi 3 Mini 128K Instruct on Ryzen AI Max+ 395 128 GB report
RTX Spark8-bit128K51 tok/s0.3 sPDF: Phi 3 Mini 128K Instruct on RTX Spark report
DGX Spark8-bit128K46 tok/s0.3 sPDF: Phi 3 Mini 128K Instruct on DGX Spark report
Dual DGX Spark8-bit128K46 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on Dual DGX Spark report
DGX Station GB3008-bit128K570 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on DGX Station GB300 report
2× RTX PRO 6000 Blackwell8-bit128K243 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 Blackwell8-bit128K243 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 Blackwell8-bit128K243 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXM8-bit128K268 tok/s0.2 sPDF: Phi 3 Mini 128K Instruct on A100 80 GB SXM report
H100 SXM8-bit128K378 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on H100 SXM report
4× H200 NVL8-bit128K468 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 4× H200 NVL report
8× H200 NVL8-bit128K468 tok/s0.1 sPDF: Phi 3 Mini 128K Instruct on 8× H200 NVL report

Best fit is the highest quality, up to 8-bit, that leaves 16K of context. First reply is the wait for a 2K prompt. Speeds are rough, plus or minus 25%.

How to run it

llama.cpp
llama-server -hf bartowski/Phi-3.1-mini-128k-instruct-GGUF
vLLM
vllm serve microsoft/Phi-3-mini-128k-instruct

Questions

How much VRAM does Phi 3 Mini 128K Instruct need?

Phi 3 Mini 128K Instruct needs 2.2 GB for its weights at 4-bit, 5.8 GB with an 8K context and 14.8 GB with 32K. At 8-bit, 7.4 GB.

What is the minimum VRAM for Phi 3 Mini 128K Instruct?

About 5.3 GB at 3-bit with an 8K context, the lowest precision we recommend for a model this size. The smallest machine here that runs it without spilling is the RTX 3080 10 GB.

How big is Phi 3 Mini 128K Instruct?

3.8B parameters: 7.1 GB of weights at 16-bit, 2.2 GB at 4-bit.

Can Phi 3 Mini 128K Instruct run on an RTX 4090?

Yes. At 8-bit it holds 48K of context and writes about 152 tokens a second.

More models