PH

phi 3 22b 128k i1

PhiGGUF by mradermacherUpdated 2024-09-13
Download on Hugging Face
Parameters22B
Context128K
Layers64
Architecturephi3
Smallest quant4.6 GB
Quick answer

phi 3 22b 128k i1 needs about 16.8 GB of memory at Q4_K_M (a 13.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 4.6 GB (IQ1_S) to 18.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Phi 3 22B 128K i1 – 22B parameter LLM with 128K context

Phi 3 22B 128K i1 is a 22B parameter language model with a 131072 token context window. It is released under the MIT license and is available in multiple GGUF quantizations. The model supports a wide range of languages and tasks.

Good at

  • Large context handling
  • High token throughput
  • Versatile language support

Limits

  • No vision capabilities
  • Requires substantial VRAM for higher quants
  • No mixture of experts

Best for

  • Long-form content generation
  • Complex reasoning tasks
  • Large context summarization

Who it’s for. Developers and researchers who need a large language model with an extended context window. The model is suitable for applications that require deep contextual understanding and high token limits.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.6 GB 7.8 GB
Tight Get file →
IQ1_M5.1 GB 8.3 GB
Too big Get file →
IQ2_XXS5.8 GB 9.0 GB
Too big Get file →
IQ2_XS6.5 GB 9.7 GB
Too big Get file →
IQ2_S6.8 GB 10.0 GB
Too big Get file →
IQ2_M7.4 GB 10.6 GB
Too big Get file →
Q2_K8.1 GB 11.3 GB
Too big Get file →
IQ3_XXS8.6 GB 11.8 GB
Too big Get file →
IQ3_XS9.2 GB 12.4 GB
Too big Get file →
IQ3_S9.6 GB 12.8 GB
Too big Get file →
Q3_K_S9.6 GB 12.8 GB
Too big Get file →
IQ3_M10.2 GB 13.4 GB
Too big Get file →
Q3_K_M11.0 GB 14.1 GB
Too big Get file →
IQ4_XS11.8 GB 15.0 GB
Too big Get file →
Q3_K_L11.9 GB 15.0 GB
Too big Get file →
Q4_012.5 GB 15.7 GB
Too big Get file →
Q4_K_S12.6 GB 15.8 GB
Too big Get file →
Q4_K_M13.6 GB 16.8 GB
Too big Get file →
Q5_K_S15.2 GB 18.4 GB
Too big Get file →
Q5_K_M16.0 GB 19.2 GB
Too big Get file →
Q6_K18.2 GB 21.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M. For 12 GB VRAM, IQ2_S or Q2_K are suitable. For 16 GB VRAM, Q4_K_M or Q5_K_S provide a good balance of size and performance. Memory estimates are approximate.

What GPU do you need for phi 3 22b 128k i1?

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 IQ1_S (4.6 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ3_XXS (8.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (12.6 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.2 GB file, about 21.3 GB in use).

Which phi 3 22b 128k i1 quant should you choose?

Q4_K_M is the usual starting point for phi 3 22b 128k i1: it balances file size and quality well. Here it is a 13.6 GB file.

If memory is tight, the smallest file is IQ1_S at 4.6 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

Architecturephi3
Parameters22B
Layers64
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyPhi
Licensemit
Downloads (HF)1,392
Last updated2024-09-13

Frequently asked questions about phi 3 22b 128k i1

How much VRAM does phi 3 22b 128k i1 need?

About 16.8 GB at Q4_K_M with an 8K context window. That is the 13.6 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 phi 3 22b 128k i1 on an 8 GB GPU?

Yes, with IQ1_S: the 4.6 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 phi 3 22b 128k i1 GGUF?

It depends on the quant: IQ1_S is 4.6 GB, IQ1_M is 5.1 GB, IQ2_XXS is 5.8 GB, IQ2_XS is 6.5 GB, IQ2_S is 6.8 GB, IQ2_M is 7.4 GB and 15 more.

What context length does phi 3 22b 128k i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download phi 3 22b 128k i1 GGUF?

The files are on Hugging Face in the mradermacher/phi-3-22b-128k-i1-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 phi 3 22b 128k i1 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 the IQ1_S or IQ1_M quantization will fit within 8 GB VRAM, with estimated memory usage around 7.8–8.3 GB at 8 k context.

Does this model support vision tasks?

No, Phi 3 22B 128K i1 does not include vision capabilities.

What license does this model use?

The model is released under the MIT license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other medium models

All medium models →