PH

Phonellm Alpha 1

PhonellmGGUF by mradermacherUpdated 2026-08-30
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant0.1 GB
Quick answer

Phonellm Alpha 1 needs about 32.0 GB of memory at Q4_K_M (a 24.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.1 GB to 33.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

Phonellm Alpha 1 – a 31.6B‑parameter MoE model for voice agents

Phonellm Alpha 1 is a 31.6B‑parameter mixture‑of‑experts model based on Nemotron. It is fine‑tuned for phone‑agent workloads and released under a BSD‑2‑clause license. The model supports reasoning and tool use.

Good at

  • Voice‑centric dialogue
  • Reasoning tasks
  • Tool integration

Limits

  • Large VRAM requirement for full precision
  • No vision support
  • Requires 1,048,576 token context

Best for

  • Customer service call centers
  • Healthcare voice assistants
  • Retail support agents

Who it’s for. Developers building low‑latency voice agents who need an open‑weight model. The model can be run on custom infrastructure and is free of commercial restrictions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 7.5 GB
Tight Get file →
IQ1_S17.9 GB 25.3 GB
Too big Get file →
IQ1_M17.9 GB 25.3 GB
Too big Get file →
IQ2_XXS17.9 GB 25.4 GB
Too big Get file →
IQ2_XS17.9 GB 25.4 GB
Too big Get file →
IQ2_S17.9 GB 25.4 GB
Too big Get file →
IQ2_M17.9 GB 25.4 GB
Too big Get file →
Q2_K17.9 GB 25.4 GB
Too big Get file →
IQ3_XXS17.9 GB 25.4 GB
Too big Get file →
IQ3_S17.9 GB 25.4 GB
Too big Get file →
IQ3_XS17.9 GB 25.4 GB
Too big Get file →
Q3_K_S17.9 GB 25.4 GB
Too big Get file →
IQ4_XS18.0 GB 25.4 GB
Too big Get file →
Q4_018.1 GB 25.5 GB
Too big Get file →
Q2_K_S18.1 GB 25.5 GB
Too big Get file →
IQ3_M18.1 GB 25.6 GB
Too big Get file →
Q3_K_M19.8 GB 27.3 GB
Too big Get file →
Q4_119.9 GB 27.4 GB
Too big Get file →
Q3_K_L20.7 GB 28.2 GB
Too big Get file →
Q4_K_S21.9 GB 29.4 GB
Too big Get file →
Q5_K_S23.8 GB 31.3 GB
Too big Get file →
Q4_K_M24.5 GB 32.0 GB
Too big Get file →
Q5_K_M26.0 GB 33.5 GB
Too big Get file →
Q6_K33.5 GB 41.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (17.86 GB file, 25.3 GB memory at 8 k context). For 16 GB VRAM, IQ2_M (17.91 GB file, 25.4 GB memory). For 32 GB VRAM, Q4_K_M (24.52 GB file, 32 GB memory). Estimates are approximate.

What GPU do you need for Phonellm Alpha 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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (24.5 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (33.5 GB file, about 41.0 GB in use).

Which Phonellm Alpha 1 quant should you choose?

Q4_K_M is the usual starting point for Phonellm Alpha 1: it balances file size and quality well. Here it is a 24.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 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

Architecturenemotron_h_moe
Parameters31.6B (approximate, mixture of experts)
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized bymradermacher
FamilyPhonellm
Downloads (HF)713
Last updated2026-08-30

Frequently asked questions about Phonellm Alpha 1

How much VRAM does Phonellm Alpha 1 need?

About 32.0 GB at Q4_K_M with an 8K context window. That is the 24.5 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 Phonellm Alpha 1 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phonellm Alpha 1 GGUF?

It depends on the quant: file is 0.1 GB, IQ1_S is 17.9 GB, IQ1_M is 17.9 GB, IQ2_XXS is 17.9 GB, IQ2_XS is 17.9 GB, IQ2_S is 17.9 GB and 18 more.

What context length does Phonellm Alpha 1 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 27.9 GB at 32K.

Where can I download Phonellm Alpha 1 GGUF?

The files are on Hugging Face in the mradermacher/phonellm-alpha-1-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 Phonellm Alpha 1 use?

Hugging Face lists the license as bsd-2-clause. 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 Phonellm Alpha 1 on 8 GB VRAM?

The smallest quant for 8 GB VRAM is IQ1_S, which requires about 25.3 GB of VRAM at 8 k context. It is not feasible on 8 GB VRAM.

Does the model support vision tasks?

No, Phonellm Alpha 1 does not support vision capabilities.

Other GGUFs of phonellm-alpha-1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phonellm models

All Phonellm →

Other medium models

All medium models →