PH

EXP Phi4 Instruct STM32Lx

PhiGGUF by mradermacherUpdated 2025-01-15
Download on Hugging Face
Parameters14.7B
Context16K
Layers40
Architecturellama
Smallest quant5.6 GB
Quick answer

EXP Phi4 Instruct STM32Lx needs about 11.1 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 5.6 GB (Q2_K) to 15.6 GB (Q8_0).

EXP Phi4 Instruct STM32Lx is a 14.7B-parameter Phi model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 11 quant files, from 5.6 GB (Q2_K) to 15.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.6 GB 7.8 GB
Tight Get file →
Q3_K_S6.5 GB 8.7 GB
Too big Get file →
Q3_K_M7.2 GB 9.4 GB
Too big Get file →
Q3_K_L7.8 GB 10.0 GB
Too big Get file →
IQ4_XS8.1 GB 10.2 GB
Too big Get file →
Q4_K_S8.4 GB 10.6 GB
Too big Get file →
Q4_K_M8.9 GB 11.1 GB
Too big Get file →
Q5_K_S10.2 GB 12.3 GB
Too big Get file →
Q5_K_M10.4 GB 12.6 GB
Too big Get file →
Q6_K12.0 GB 14.2 GB
Too big Get file →
Q8_015.6 GB 17.8 GB
Too big Get file →

What GPU do you need for EXP Phi4 Instruct STM32Lx?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q2_K (5.6 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (8.9 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.6 GB file, about 17.8 GB in use).

Which EXP Phi4 Instruct STM32Lx quant should you choose?

Q4_K_M is the usual starting point for EXP Phi4 Instruct STM32Lx: it balances file size and quality well. Here it is a 8.9 GB file.

The Q8_0 file is 15.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 5.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters14.7B
Layers40
Trained context16,384 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymradermacher
FamilyPhi
Licenseapache-2.0
Downloads (HF)46
Last updated2025-01-15

Frequently asked questions about EXP Phi4 Instruct STM32Lx

How much VRAM does EXP Phi4 Instruct STM32Lx need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run EXP Phi4 Instruct STM32Lx on an 8 GB GPU?

Yes, with Q2_K: the 5.6 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of EXP Phi4 Instruct STM32Lx GGUF?

It depends on the quant: Q2_K is 5.6 GB, Q3_K_S is 6.5 GB, Q3_K_M is 7.2 GB, Q3_K_L is 7.8 GB, IQ4_XS is 8.1 GB, Q4_K_S is 8.4 GB and 5 more.

What context length does EXP Phi4 Instruct STM32Lx support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.

Where can I download EXP Phi4 Instruct STM32Lx GGUF?

The files are on Hugging Face in the mradermacher/EXP-Phi4-Instruct-STM32Lx-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does EXP Phi4 Instruct STM32Lx use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other medium models

All medium models →