PH

FC PHI 3.5 Mini Merged 1

PhiGGUF by mradermacherUpdated 2024-09-16
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturellama
Smallest quant1.4 GB
Quick answer

FC PHI 3.5 Mini Merged 1 needs about 6.0 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.4 GB (Q2_K) to 7.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

FC PHI 3.5 Mini Merged 1 – a 3.82B llama model in GGUF format

FC PHI 3.5 Mini Merged 1 is a 3.82B parameter llama model fine‑tuned from unsloth/Phi-3.5-mini-instruct. It supports a 131072 token context window and is released under the apache-2.0 license. The model is available in multiple static quantizations for efficient deployment.

Good at

  • Large context handling
  • Efficient inference with low‑bit quants
  • Stable performance on 8‑k token prompts

Limits

  • No vision or multimodal support
  • Requires at least 5.2 GB VRAM for Q2_K at 8 k context
  • No mixture‑of‑experts architecture

Best for

  • Chatbots needing long context
  • Fine‑tuning on custom datasets
  • Running on consumer GPUs with limited VRAM

Who it’s for. Developers and researchers who need a compact Phi‑style model with a large context window. The model is suitable for local deployment on machines with 8 GB or more VRAM. It is ideal for those who prefer open‑source, apache‑licensed models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 5.2 GB
Fits Get file →
IQ3_XS1.6 GB 5.3 GB
Fits Get file →
IQ3_S1.7 GB 5.4 GB
Fits Get file →
Q3_K_S1.7 GB 5.4 GB
Fits Get file →
IQ3_M1.8 GB 5.5 GB
Fits Get file →
Q3_K_M1.9 GB 5.6 GB
Fits Get file →
Q3_K_L2.0 GB 5.8 GB
Fits Get file →
IQ4_XS2.1 GB 5.8 GB
Fits Get file →
Q4_K_S2.2 GB 5.9 GB
Fits Get file →
Q4_K_M2.3 GB 6.0 GB
Fits Get file →
Q5_K_S2.6 GB 6.4 GB
Fits Get file →
Q5_K_M2.7 GB 6.4 GB
Fits Get file →
Q6_K3.1 GB 6.9 GB
Fits Get file →
Q8_04.1 GB 7.8 GB
Tight Get file →
F167.6 GB 11.4 GB
Too big Get file →

For 8 GB VRAM, Q2_K (1.45 GB) or IQ3_XS (1.6 GB) are good choices, estimating 5.2–5.3 GB memory at 8 k context. If you have 12 GB VRAM, Q4_K_M (2.32 GB) or Q5_K_M (2.72 GB) provide a balance of size and quality. Higher‑bit quants like Q8_0 (4.06 GB) or F16 (7.64 GB) require more memory but offer better precision.

What GPU do you need for FC PHI 3.5 Mini Merged 1?

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: the best quant that fits is Q4_K_M (2.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).

Which FC PHI 3.5 Mini Merged 1 quant should you choose?

Q4_K_M is the usual starting point for FC PHI 3.5 Mini Merged 1: it balances file size and quality well. Here it is a 2.3 GB file.

The Q8_0 file is 4.1 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 1.4 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
Parameters3.82B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilyPhi
Licenseapache-2.0
Downloads (HF)2,319
Last updated2024-09-16

Frequently asked questions about FC PHI 3.5 Mini Merged 1

How much VRAM does FC PHI 3.5 Mini Merged 1 need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.3 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 FC PHI 3.5 Mini Merged 1 on an 8 GB GPU?

Yes, with Q8_0: the 4.1 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 FC PHI 3.5 Mini Merged 1 GGUF?

It depends on the quant: Q2_K is 1.4 GB, IQ3_XS is 1.6 GB, IQ3_S is 1.7 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.8 GB, Q3_K_M is 1.9 GB and 9 more.

What context length does FC PHI 3.5 Mini Merged 1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download FC PHI 3.5 Mini Merged 1 GGUF?

The files are on Hugging Face in the mradermacher/FC-PHI-3.5-Mini-Merged-1-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 FC PHI 3.5 Mini Merged 1 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.

Can I run FC PHI 3.5 Mini Merged 1 on 8 GB VRAM?

Yes, using Q2_K or IQ3_XS quants will fit within 8 GB VRAM, with estimated memory usage around 5.2–5.3 GB at 8 k context.

Does this model support vision or multimodal inputs?

No, the model is purely text‑based and does not include vision or multimodal capabilities.

What license applies to this model?

The model is released under the apache-2.0 license, allowing free use and modification.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other small models

All small models →