PH

Phonellm Mini Alpha 2

PhonellmGGUF by mradermacherUpdated 2026-10-16
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant17.9 GB
Quick answer

Phonellm Mini Alpha 2 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 11 quants, from 17.9 GB (Q2_K) to 33.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

Phonellm Mini Alpha 2 – a fast, 31.6B‑parameter text model for voice agents

Phonellm Mini Alpha 2 is a 31.6B‑parameter model based on NVIDIA Nemotron 3 Nano. It supports reasoning and tool calling and is optimized for speed in voice agent pipelines. The model is released under the BSD‑2‑Clause license.

Good at

  • Fast inference on GPUs
  • Tool calling
  • Reasoning tasks

Limits

  • No vision support
  • Requires 8‑k context for estimates
  • Large VRAM needed for higher quants

Best for

  • Voice assistant back‑ends
  • Tool‑enabled chatbots
  • Rapid prototyping of LLM services

Who it’s for. Developers building voice‑enabled agents who need a lightweight, high‑throughput language model. The model is suitable for integration into existing pipelines that use llama.cpp or vLLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.9 GB 25.4 GB
Too big Get file →
Q3_K_S17.9 GB 25.4 GB
Too big Get file →
IQ4_XS18.2 GB 25.7 GB
Too big Get file →
Q3_K_M19.8 GB 27.3 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 →
Q8_033.6 GB 41.1 GB
Too big Get file →

For 8‑GB VRAM use Q2_K (file size 17.91 GB, estimated 25.4 GB memory). For 12‑GB VRAM Q3_K_S (17.93 GB, 25.4 GB) or IQ4_XS (18.21 GB, 25.7 GB). For 16‑GB VRAM Q4_K_S (21.92 GB, 29.4 GB) or Q4_K_M (24.52 GB, 32 GB). Higher quants require more memory.

What GPU do you need for Phonellm Mini Alpha 2?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 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 Q8_0 (33.6 GB file, about 41.1 GB in use).

Which Phonellm Mini Alpha 2 quant should you choose?

Q4_K_M is the usual starting point for Phonellm Mini Alpha 2: it balances file size and quality well. Here it is a 24.5 GB file.

The Q8_0 file is 33.6 GB, about 1.4 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 17.9 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

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)2,974
Last updated2026-10-16

Frequently asked questions about Phonellm Mini Alpha 2

How much VRAM does Phonellm Mini Alpha 2 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 Mini Alpha 2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Phonellm Mini Alpha 2 GGUF?

It depends on the quant: Q2_K is 17.9 GB, Q3_K_S is 17.9 GB, IQ4_XS is 18.2 GB, Q3_K_M is 19.8 GB, Q3_K_L is 20.7 GB, Q4_K_S is 21.9 GB and 5 more.

What context length does Phonellm Mini Alpha 2 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 Mini Alpha 2 GGUF?

The files are on Hugging Face in the mradermacher/phonellm-mini-alpha-2-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 Mini Alpha 2 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 Mini Alpha 2 on 8 GB VRAM?

Yes, using the Q2_K quant which estimates 25.4 GB memory at 8‑k context, but actual VRAM usage may be lower with efficient batching.

Does the model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the BSD‑2‑Clause license.

Other GGUFs of phonellm-mini-alpha-2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phonellm models

All Phonellm →

Other medium models

All medium models →