PE

Pebble 1 30B

PebbleGGUF by mradermacherUpdated 2026-10-20
Download on Hugging Face
Parameters27.9B
Context128K
Layers52
Architecturemuse-glimmer
Smallest quant0.0 GB
Quick answer

Pebble 1 30B needs about 17.9 GB of memory at Q4_K_M (a 16.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Pebble 1 30B – a 27.9B parameter reasoning model

Pebble 1 30B is a 27.9B parameter model fine‑tuned from Muse‑Glimmer‑30B. It is designed for factual reasoning and can abstain when uncertain. The model is open‑source under Apache‑2.0.

Good at

  • factual reasoning
  • abstaining from uncertain answers
  • tool usage

Limits

  • trained context 131072 tokens
  • no vision support in GGUF
  • requires large VRAM for higher quants

Best for

  • question answering with high confidence
  • knowledge‑base queries
  • assistant tasks that need safe responses

Who it’s for. Developers building assistants that need reliable factual answers and can tolerate abstentions. Researchers interested in calibrated reasoning models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
IQ1_S6.5 GB 7.5 GB
Tight Get file →
IQ1_M7.1 GB 8.0 GB
Tight Get file →
IQ2_XXS8.0 GB 8.9 GB
Too big Get file →
IQ2_XS8.7 GB 9.7 GB
Too big Get file →
IQ2_S9.1 GB 10.1 GB
Too big Get file →
IQ2_M9.8 GB 10.8 GB
Too big Get file →
Q2_K_S10.0 GB 11.0 GB
Too big Get file →
Q2_K10.7 GB 11.6 GB
Too big Get file →
IQ3_XXS11.1 GB 12.1 GB
Too big Get file →
IQ3_XS12.0 GB 12.9 GB
Too big Get file →
Q3_K_S12.5 GB 13.4 GB
Too big Get file →
IQ3_S12.5 GB 13.5 GB
Too big Get file →
IQ3_M12.8 GB 13.8 GB
Too big Get file →
Q3_K_M13.7 GB 14.6 GB
Too big Get file →
Q3_K_L14.7 GB 15.6 GB
Too big Get file →
IQ4_XS15.2 GB 16.2 GB
Too big Get file →
Q4_016.1 GB 17.0 GB
Too big Get file →
Q4_K_S16.1 GB 17.1 GB
Too big Get file →
Q4_K_M16.9 GB 17.9 GB
Too big Get file →
Q4_117.7 GB 18.6 GB
Too big Get file →
Q5_K_S19.3 GB 20.3 GB
Too big Get file →
Q5_K_M19.8 GB 20.7 GB
Too big Get file →
Q6_K22.9 GB 23.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.53 GB, 7.5 GB memory) or IQ1_M (7.06 GB, 8 GB memory). With 16 GB VRAM, Q4_K_M (16.94 GB, 17.9 GB memory) is suitable. Larger GPUs can run Q5_K_M or Q6_K for higher quality.

What GPU do you need for Pebble 1 30B?

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 the main file (0.0 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ1_M (7.1 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_K (10.7 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_L (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (22.9 GB file, about 23.8 GB in use).

Which Pebble 1 30B quant should you choose?

Q4_K_M is the usual starting point for Pebble 1 30B: it balances file size and quality well. Here it is a 16.9 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

Architecturemuse-glimmer
Parameters27.9B
Layers52
Trained context131,072 tokens
KV cache (fp16)52 KB per token

Source

Quantized bymradermacher
FamilyPebble
Licenseapache-2.0
Downloads (HF)1,435
Last updated2026-10-20

Frequently asked questions about Pebble 1 30B

How much VRAM does Pebble 1 30B need?

About 17.9 GB at Q4_K_M with an 8K context window. That is the 16.9 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 Pebble 1 30B on an 8 GB GPU?

Yes, with IQ1_M: the 7.1 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 Pebble 1 30B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 6.5 GB, IQ1_M is 7.1 GB, IQ2_XXS is 8.0 GB, IQ2_XS is 8.7 GB, IQ2_S is 9.1 GB and 18 more.

What context length does Pebble 1 30B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download Pebble 1 30B GGUF?

The files are on Hugging Face in the mradermacher/Pebble-1-30B-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 Pebble 1 30B use?

Hugging Face lists the license as apache-2.0. 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 Pebble 1 30B on a single 8 GB GPU?

Use the IQ1_S or IQ1_M quant; they fit within 8 GB VRAM and use about 7.5–8 GB memory at 8k context.

Does the model support vision?

The GGUF files do not include vision support; the model is text‑only in this format.

What license applies to Pebble 1 30B?

The model is released under the Apache‑2.0 license.

Other GGUFs of Pebble-1-30B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Pebble models

All Pebble →

Other medium models

All medium models →