GE

Tiger Gemma 9B v1

GemmaGGUF by TheDrummerUpdated 2024-07-12
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant3.8 GB
Quick answer

Tiger Gemma 9B v1 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 7 quants, from 3.8 GB (Q2_K) to 18.5 GB (F16).

Tiger Gemma 9B v1 – a 9.24B parameter Gemma model

Tiger Gemma 9B v1 is a 9.24B parameter Gemma2 model. It supports a 8192 token context window. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Low memory variants
  • Fast inference on CPU

Limits

  • No license information
  • No vision support
  • No mixture of experts

Best for

  • Chat applications
  • Text generation
  • Fine‑tuning small projects

Who it’s for. Developers and researchers who need a large Gemma model with flexible quantization options. Suitable for local deployment on machines with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.8 GB 7.1 GB
Fits Get file →
Q3_K_M4.8 GB 8.1 GB
Too big Get file →
Q4_K_M5.8 GB 9.1 GB
Too big Get file →
Q5_K_M6.6 GB 10.0 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 →
F1618.5 GB 21.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.76 GB file, ~9.1 GB memory). For 12 GB VRAM, Q5_K_M (6.65 GB file, ~10 GB memory) is a good balance. For 16 GB VRAM, Q6_K (7.59 GB file, ~10.9 GB memory) offers higher precision.

What GPU do you need for Tiger Gemma 9B v1?

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 Q2_K (3.8 GB file, about 7.1 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 F16 (18.5 GB file, about 21.8 GB in use).

Which Tiger Gemma 9B v1 quant should you choose?

Q4_K_M is the usual starting point for Tiger Gemma 9B v1: 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 byTheDrummer
FamilyGemma
Downloads (HF)734
Last updated2024-07-12

Frequently asked questions about Tiger Gemma 9B v1

How much VRAM does Tiger Gemma 9B v1 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 Tiger Gemma 9B v1 on an 8 GB GPU?

Yes, with Q2_K: the 3.8 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tiger Gemma 9B v1 GGUF?

It depends on the quant: Q2_K is 3.8 GB, Q3_K_M is 4.8 GB, Q4_K_M is 5.8 GB, Q5_K_M is 6.6 GB, Q6_K is 7.6 GB, Q8_0 is 9.8 GB and 1 more.

What context length does Tiger Gemma 9B v1 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 Tiger Gemma 9B v1 GGUF?

The files are on Hugging Face in the TheDrummer/Tiger-Gemma-9B-v1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Tiger Gemma 9B v1 on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 9.1 GB memory at 8K context, which fits within 8 GB VRAM with some overhead.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a 8192 token context window.

Similar models

Browse all →

More from TheDrummer

All by TheDrummer →

More Gemma models

All Gemma →

Other small models

All small models →