PH

calme-2.1-phi3.5-4b

PhiGGUF by QuantFactoryUpdated 2024-09-04
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant1.4 GB
Quick answer

calme-2.1-phi3.5-4b needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 1.4 GB (Q2_K) to 4.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Phi-3.5-mini instruction‑tuned model with 128K context

calme‑2.1‑phi3.5‑4b is a 3.82 billion‑parameter Phi‑3.5‑mini model fine‑tuned for instruction following. It supports a 131072‑token context window and is released under the MIT license.

Good at

  • High‑quality reasoning
  • Instruction compliance
  • Low‑latency inference

Limits

  • No vision support
  • Requires 128K context for full capability
  • No multilingual support listed

Best for

  • Chatbots in constrained environments
  • Code and math reasoning tasks
  • Research prototypes

Who it’s for. Developers building lightweight instruction‑driven applications who need a large context window and low latency. The model is suitable for commercial and research use under the MIT license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 5.1 GB
Fits Get file →
Q3_K_S1.7 GB 5.4 GB
Fits Get file →
Q3_K_M2.0 GB 5.7 GB
Fits Get file →
Q3_K_L2.1 GB 5.8 GB
Fits Get file →
Q4_02.2 GB 5.9 GB
Fits Get file →
Q4_K_S2.2 GB 5.9 GB
Fits Get file →
Q4_K_M2.4 GB 6.1 GB
Fits Get file →
Q4_12.4 GB 6.1 GB
Fits Get file →
Q5_02.6 GB 6.4 GB
Fits Get file →
Q5_K_S2.6 GB 6.4 GB
Fits Get file →
Q5_K_M2.8 GB 6.5 GB
Fits Get file →
Q5_12.9 GB 6.6 GB
Fits Get file →
Q6_K3.1 GB 6.9 GB
Fits Get file →
Q8_04.1 GB 7.8 GB
Tight Get file →

For 8 GB VRAM, use Q4_0 (2.18 GB, 5.9 GB memory at 8k context) or Q4_K_S (2.19 GB, 5.9 GB). For 12 GB VRAM, Q5_0 (2.64 GB, 6.4 GB) or Q5_K_S (2.64 GB, 6.4 GB) are suitable. Larger VRAM allows Q6_K (3.14 GB, 6.9 GB) or Q8_0 (4.06 GB, 7.8 GB).

What GPU do you need for calme-2.1-phi3.5-4b?

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_S (2.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).

Which calme-2.1-phi3.5-4b quant should you choose?

Q4_K_M is the usual starting point for calme-2.1-phi3.5-4b: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 4.1 GB, about 1.7 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

Architecturephi3
Parameters3.82B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byQuantFactory
FamilyPhi
Licensemit
Downloads (HF)1,017
Last updated2024-09-04

Frequently asked questions about calme-2.1-phi3.5-4b

How much VRAM does calme-2.1-phi3.5-4b need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 calme-2.1-phi3.5-4b 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 calme-2.1-phi3.5-4b GGUF?

It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.7 GB, Q3_K_M is 2.0 GB, Q3_K_L is 2.1 GB, Q4_0 is 2.2 GB, Q4_K_S is 2.2 GB and 8 more.

What context length does calme-2.1-phi3.5-4b 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 calme-2.1-phi3.5-4b GGUF?

The files are on Hugging Face in the QuantFactory/calme-2.1-phi3.5-4b-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 calme-2.1-phi3.5-4b use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantizations which fit within 8 GB VRAM and use about 5.9 GB memory at 8k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What context length does it support?

It supports a 131072‑token context window, enabling 128K token context.

Other GGUFs of Phi-3.5-mini-instruct

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Phi models

All Phi →

Other small models

All small models →