PH

Tess v2.5 Phi 3 medium 128k 14B

PhiGGUF by mradermacherUpdated 2024-06-18
Download on Hugging Face
Parameters14B
Context128K
Layers40
Architecturephi3
Smallest quant5.1 GB
Quick answer

Tess v2.5 Phi 3 medium 128k 14B needs about 10.7 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 5.1 GB (Q2_K) to 27.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.

Tess v2.5 Phi 3 medium 128k 14B – 14B parameter Phi3 model

Tess v2.5 Phi 3 medium 128k 14B is a 14B parameter Phi3 architecture model trained on 131072 context tokens. It is released under the MIT license and supports the ChatML prompt format.

Good at

  • Large context handling
  • Phi3 architecture strengths
  • ChatML compatibility

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

  • Chat applications with long context
  • Research on Phi3 models
  • Low‑latency inference on moderate GPUs

Who it’s for. Developers and researchers needing a 14B Phi3 model with extensive context. The model is suitable for local deployment and experimentation with GGUF quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.1 GB 7.3 GB
Tight Get file →
IQ3_XS5.8 GB 8.0 GB
Tight Get file →
IQ3_S6.1 GB 8.2 GB
Too big Get file →
Q3_K_S6.1 GB 8.2 GB
Too big Get file →
IQ3_M6.5 GB 8.7 GB
Too big Get file →
Q3_K_M6.9 GB 9.1 GB
Too big Get file →
Q3_K_L7.5 GB 9.7 GB
Too big Get file →
IQ4_XS7.5 GB 9.7 GB
Too big Get file →
Q4_K_S8.0 GB 10.1 GB
Too big Get file →
Q4_K_M8.6 GB 10.7 GB
Too big Get file →
Q5_K_S9.6 GB 11.8 GB
Too big Get file →
Q5_K_M10.1 GB 12.3 GB
Too big Get file →
Q6_K11.5 GB 13.6 GB
Too big Get file →
Q8_014.8 GB 17.0 GB
Too big Get file →
F1627.9 GB 30.1 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (5.14 GB file, 7.3 GB memory) or IQ3_XS (5.81 GB file, 8 GB memory). For 12 GB VRAM, Q4_K_M (8.57 GB file, 10.7 GB memory) or Q5_K_S (9.62 GB file, 11.8 GB memory) are suitable. Higher quants like Q6_K or Q8_0 require more than 13 GB VRAM.

What GPU do you need for Tess v2.5 Phi 3 medium 128k 14B?

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 IQ3_XS (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (9.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.5 GB file, about 13.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 17.0 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (27.9 GB file, about 30.1 GB in use).

Which Tess v2.5 Phi 3 medium 128k 14B quant should you choose?

Q4_K_M is the usual starting point for Tess v2.5 Phi 3 medium 128k 14B: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 14.8 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 5.1 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
Parameters14B
Layers40
Trained context131,072 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymradermacher
FamilyPhi
Licensemit
Downloads (HF)1,455
Last updated2024-06-18

Frequently asked questions about Tess v2.5 Phi 3 medium 128k 14B

How much VRAM does Tess v2.5 Phi 3 medium 128k 14B need?

About 10.7 GB at Q4_K_M with an 8K context window. That is the 8.6 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 Tess v2.5 Phi 3 medium 128k 14B on an 8 GB GPU?

Yes, with IQ3_XS: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tess v2.5 Phi 3 medium 128k 14B GGUF?

It depends on the quant: Q2_K is 5.1 GB, IQ3_XS is 5.8 GB, IQ3_S is 6.1 GB, Q3_K_S is 6.1 GB, IQ3_M is 6.5 GB, Q3_K_M is 6.9 GB and 9 more.

What context length does Tess v2.5 Phi 3 medium 128k 14B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.

Where can I download Tess v2.5 Phi 3 medium 128k 14B GGUF?

The files are on Hugging Face in the mradermacher/Tess-v2.5-Phi-3-medium-128k-14B-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 Tess v2.5 Phi 3 medium 128k 14B 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 Tess v2.5 Phi 3 medium 128k 14B on 8 GB VRAM?

Yes, using Q2_K or IQ3_XS quantizations fits within 8 GB VRAM with approximate memory usage of 7.3–8 GB.

Does this model support vision tasks?

No, the model has no vision capabilities.

What prompt format does it use?

It uses the ChatML prompt format as specified in the parent model card.

Other GGUFs of Tess-v2.5-Phi-3-medium-128k-14B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other medium models

All medium models →