GE

Tiger Gemma 9B v2

GemmaGGUF by bartowskiUpdated 2024-09-04
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant3.4 GB
Quick answer

Tiger Gemma 9B v2 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 24 quants, from 3.4 GB (IQ2_M) to 18.5 GB (F16).

Tiger Gemma 9B v2 – a decensored Gemma model in GGUF format

Tiger Gemma 9B v2 is a 9.24 billion‑parameter Gemma2 model. It is available in multiple llama.cpp quantizations and supports a 8192‑token context. The model is decensored and has no system prompt support.

Good at

  • Decensored responses
  • Gemma architecture consistency
  • LLM inference via llama.cpp

Limits

  • No system prompt support
  • License not specified
  • No vision capabilities

Best for

  • Chat applications
  • Text generation tasks
  • Rapid prototyping with low‑memory quants

Who it’s for. Developers and researchers who need a lightweight Gemma model for local inference. The model is suitable for users with limited GPU memory who can choose an appropriate quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M3.4 GB 6.8 GB
Fits Get file →
Q2_K3.8 GB 7.1 GB
Fits Get file →
Q2_K_L4.0 GB 7.3 GB
Tight Get file →
IQ3_XS4.1 GB 7.5 GB
Tight Get file →
Q3_K_S4.3 GB 7.7 GB
Tight Get file →
IQ3_M4.5 GB 7.8 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 →
IQ4_XS5.2 GB 8.5 GB
Too big Get file →
Q3_K_XL5.4 GB 8.7 GB
Too big Get file →
Q4_05.4 GB 8.8 GB
Too big Get file →
Q4_05.4 GB 8.8 GB
Too big Get file →
Q4_05.4 GB 8.8 GB
Too big Get file →
Q4_05.5 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_K_L6.0 GB 9.3 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_K_L6.9 GB 10.2 GB
Too big Get file →
Q6_K7.6 GB 10.9 GB
Too big Get file →
Q6_K_L7.8 GB 11.1 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 (file size 5.76 GB, estimated 9.1 GB memory). For 12 GB VRAM, Q5_K_M (6.65 GB, 10 GB memory) or Q6_K (7.59 GB, 10.9 GB memory). Higher precision quants like F16 require 21.8 GB memory and are best for high‑end GPUs.

What GPU do you need for Tiger Gemma 9B v2?

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 IQ3_M (4.5 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K_L (7.8 GB file, about 11.1 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 v2 quant should you choose?

Q4_K_M is the usual starting point for Tiger Gemma 9B v2: 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 IQ2_M at 3.4 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 bybartowski
FamilyGemma
Downloads (HF)595
Last updated2024-09-04

Frequently asked questions about Tiger Gemma 9B v2

How much VRAM does Tiger Gemma 9B v2 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 v2 on an 8 GB GPU?

Yes, with IQ3_M: the 4.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tiger Gemma 9B v2 GGUF?

It depends on the quant: IQ2_M is 3.4 GB, Q2_K is 3.8 GB, Q2_K_L is 4.0 GB, IQ3_XS is 4.1 GB, Q3_K_S is 4.3 GB, IQ3_M is 4.5 GB and 18 more.

What context length does Tiger Gemma 9B v2 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 v2 GGUF?

The files are on Hugging Face in the bartowski/Tiger-Gemma-9B-v2-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 v2 on 8 GB VRAM?

Use the Q4_K_M quant, which estimates 9.1 GB memory at 8k context. It may fit with memory optimizations.

Does the model support a system prompt?

No, the model does not support a system prompt.

What is the context length of this model?

The model supports 8192 tokens of context.

Other GGUFs of Tiger-Gemma-9B-v2

Similar models

Browse all →

More from bartowski

All by bartowski →

More Gemma models

All Gemma →

Other small models

All small models →