GE

boto-9B-GGUF

GemmaGGUF by lucianosbUpdated 2024-07-10
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant3.8 GB
Quick answer

boto-9B-GGUF needs about 9.1 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 15 quants, from 3.8 GB (Q2_K) to 18.5 GB (BF16).

Boto‑9B GGUF – a 9.24B‑parameter Gemma2 model fine‑tuned with Unsloth

Boto‑9B is a Gemma2 model with 9.24 billion parameters. It is fine‑tuned from unsloth/gemma‑2‑9b‑bnb‑4bit and released under the apache‑2.0 license. The model supports a context length of 8192 tokens.

Good at

  • Fast inference on 8‑bit GPUs
  • Low‑memory quantized variants
  • Versatile text generation

Limits

  • No vision support
  • Requires 8192‑token context
  • License is apache‑2.0

Best for

  • Chatbot back‑ends
  • Text completion scripts
  • Fine‑tuning on custom data

Who it’s for. Developers and researchers who need a lightweight Gemma2 variant for local deployment. The model is suitable for users with limited GPU memory who can use quantized versions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.8 GB 7.1 GB
Fits Get file →
Q3_K_S4.3 GB 7.7 GB
Tight Get file →
Q3_K_M4.8 GB 8.1 GB
Too big Get file →
Q3_K_L5.1 GB 8.5 GB
Too big Get file →
Q4_05.4 GB 8.8 GB
Too big Get file →
Q4_K_S5.5 GB 8.8 GB
Too big Get file →
Q4_K_M5.8 GB 9.1 GB
Too big Get file →
Q4_16.0 GB 9.3 GB
Too big Get file →
Q5_06.5 GB 9.8 GB
Too big Get file →
Q5_K_S6.5 GB 9.8 GB
Too big Get file →
Q5_K_M6.6 GB 10.0 GB
Too big Get file →
Q5_17.0 GB 10.3 GB
Too big Get file →
Q6_K7.6 GB 10.9 GB
Too big Get file →
Q8_09.8 GB 13.1 GB
Too big Get file →
BF1618.5 GB 21.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (file size 5.44 GB, memory 8.8 GB). For 12 GB VRAM, Q4_K_M (5.76 GB, 9.1 GB) or Q5_0 (6.48 GB, 9.8 GB) are suitable. Higher precision variants require more than 13 GB VRAM.

What GPU do you need for boto-9B-GGUF?

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 Q3_K_S (4.3 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.6 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 13.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (18.5 GB file, about 21.8 GB in use).

Which boto-9B-GGUF quant should you choose?

Q4_K_M is the usual starting point for boto-9B-GGUF: it balances file size and quality well. Here it is a 5.8 GB file.

The Q8_0 file is 9.8 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 3.8 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

Architecturegemma2
Parameters9.24B
Layers42
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized bylucianosb
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,011
Last updated2024-07-10

Frequently asked questions about boto-9B-GGUF

How much VRAM does boto-9B-GGUF need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 5.8 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 boto-9B-GGUF on an 8 GB GPU?

Yes, with Q3_K_S: the 4.3 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of boto-9B-GGUF GGUF?

It depends on the quant: Q2_K is 3.8 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.8 GB, Q3_K_L is 5.1 GB, Q4_0 is 5.4 GB, Q4_K_S is 5.5 GB and 9 more.

What context length does boto-9B-GGUF support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.

Where can I download boto-9B-GGUF GGUF?

The files are on Hugging Face in the lucianosb/boto-9B-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 boto-9B-GGUF 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 Boto‑9B on 8 GB VRAM?

Yes, use the Q4_0 or Q4_K_S quantization; each requires about 8.8 GB of memory at 8192 context.

Is the model licensed for commercial use?

The model is released under the apache‑2.0 license, which permits commercial use.

Does the model support image inputs?

No, Boto‑9B is a text‑only language model and has no vision capabilities.

Other GGUFs of gemma-2-9b-bnb-4bit

Similar models

Browse all →

More from lucianosb

All by lucianosb →

More Gemma models

All Gemma →

Other small models

All small models →