PH

Phi 1.5 Tele

PhiGGUF by mradermacherUpdated 2025-12-25
Download on Hugging Face
Parameters1.42B
Context2K
Layers24
Architecturephi2
Smallest quant0.0 GB
Quick answer

Phi 1.5 Tele needs about 3.0 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.2 GB (Q6_K).

Phi 1.5 Tele – a 1.42B‑parameter telecom‑focused transformer

Phi 1.5 Tele is a 1.42B‑parameter phi2 architecture model trained on 2.5B telecom tokens. It supports a 2048‑token context and is licensed under MIT. The model is suitable for fine‑tuning on telecom applications.

Good at

  • Telecom domain knowledge
  • Question answering
  • Instruction following with prompt format

Limits

  • No vision support
  • Limited instruction fine‑tuning
  • Context length 2048 tokens

Best for

  • Telecom FAQ bots
  • Domain‑specific chat assistants
  • Telecom data summarization

Who it’s for. Developers building telecom‑centric LLM applications. The model is a base that can be fine‑tuned for specific tasks. It is ideal for teams needing a lightweight, MIT‑licensed model with telecom expertise.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_S0.4 GB 1.3 GB
Fits Get file →
IQ1_M0.4 GB 1.3 GB
Fits Get file →
IQ2_XXS0.4 GB 1.3 GB
Fits Get file →
IQ2_XS0.5 GB 1.4 GB
Fits Get file →
IQ2_S0.5 GB 1.4 GB
Fits Get file →
Q2_K_S0.5 GB 1.4 GB
Fits Get file →
IQ2_M0.5 GB 1.4 GB
Fits Get file →
IQ3_XXS0.6 GB 1.5 GB
Fits Get file →
Q2_K0.6 GB 1.5 GB
Fits Get file →
IQ3_XS0.6 GB 1.5 GB
Fits Get file →
IQ3_S0.7 GB 1.6 GB
Fits Get file →
Q3_K_S0.7 GB 1.6 GB
Fits Get file →
IQ3_M0.7 GB 1.6 GB
Fits Get file →
Q3_K_M0.7 GB 1.6 GB
Fits Get file →
IQ4_XS0.8 GB 1.7 GB
Fits Get file →
Q3_K_L0.8 GB 1.7 GB
Fits Get file →
IQ4_NL0.8 GB 1.7 GB
Fits Get file →
Q4_00.8 GB 1.7 GB
Fits Get file →
Q4_K_S0.8 GB 1.7 GB
Fits Get file →
Q4_K_M0.9 GB 1.8 GB
Fits Get file →
Q4_10.9 GB 1.8 GB
Fits Get file →
Q5_K_S1.0 GB 1.9 GB
Fits Get file →
Q5_K_M1.0 GB 1.9 GB
Fits Get file →
Q6_K1.2 GB 2.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 0.89 GB, memory 3 GB). For 4 GB VRAM, choose IQ2_XS (0.47 GB, 2.6 GB). For 2 GB VRAM, IQ1_S (0.37 GB, 2.5 GB). Estimates are approximate.

What GPU do you need for Phi 1.5 Tele?

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: the best quant that fits is Q6_K (1.2 GB file, about 3.3 GB in use).

Which Phi 1.5 Tele quant should you choose?

Q4_K_M is the usual starting point for Phi 1.5 Tele: it balances file size and quality well. Here it is a 0.9 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturephi2
Parameters1.42B
Layers24
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilyPhi
Licensemit
Downloads (HF)898
Last updated2025-12-25

Frequently asked questions about Phi 1.5 Tele

How much VRAM does Phi 1.5 Tele need?

About 3.0 GB at Q4_K_M with an 8K context window. That is the 0.9 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 Phi 1.5 Tele on an 8 GB GPU?

Yes, with Q6_K: the 1.2 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 1.5 Tele GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.5 GB, IQ2_S is 0.5 GB and 19 more.

What context length does Phi 1.5 Tele support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download Phi 1.5 Tele GGUF?

The files are on Hugging Face in the mradermacher/Phi-1.5-Tele-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 1.5 Tele 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 Phi 1.5 Tele on 8 GB VRAM?

Yes, Q4_K_M requires about 3 GB of VRAM, which fits within 8 GB. The model will use the remaining memory for CPU RAM and other processes.

Does the model support image inputs?

No, Phi 1.5 Tele is a text‑only model with no vision capabilities.

What is the maximum context length?

The model was trained on a context length of 2048 tokens and supports up to that limit.

Other GGUFs of Phi-1.5-Tele

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other tiny models

All tiny models →