GE

Tess-v2.5-Gemma-2-27B-alpha

GemmaGGUF by bartowskiUpdated 2024-07-02
Download on Hugging Face
Parameters27.2B
Context8K
Layers46
Architecturegemma2
Smallest quant8.4 GB
Quick answer

Tess-v2.5-Gemma-2-27B-alpha needs about 20.2 GB of memory at Q4_K_M (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 8.4 GB (IQ2_XS) to 108.9 GB (F32).

Tess‑v2.5‑Gemma‑2‑27B‑alpha – a 27.2B Gemma2 model in GGUF format

Tess‑v2.5‑Gemma‑2‑27B‑alpha is a 27.2B‑parameter Gemma2 model quantized for llama.cpp. It supports a 8192‑token context and is available in multiple quantizations ranging from IQ2_XS to Q8_0. The model is released under the gemma license.

Good at

  • Large‑context generation
  • High‑parameter density
  • Versatile quantization options

Limits

  • No vision support
  • Requires 8‑k context for estimates
  • License restricts commercial use

Best for

  • Research prototyping
  • Low‑budget inference
  • Fine‑tuning experiments

Who it’s for. Developers and researchers needing a large Gemma2 model that can run on consumer hardware with quantization. The model is suitable for those who can manage the license terms and have a GPU with sufficient VRAM for the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XS8.4 GB 12.0 GB
Too big Get file →
IQ2_S8.7 GB 12.2 GB
Too big Get file →
IQ2_M9.4 GB 13.0 GB
Too big Get file →
Q2_K10.4 GB 14.0 GB
Too big Get file →
IQ3_XXS10.8 GB 14.3 GB
Too big Get file →
IQ3_XS11.6 GB 15.1 GB
Too big Get file →
Q2_K_L11.8 GB 15.4 GB
Too big Get file →
Q3_K_S12.2 GB 15.8 GB
Too big Get file →
IQ3_M12.5 GB 16.0 GB
Too big Get file →
Q3_K_M13.4 GB 17.0 GB
Too big Get file →
Q3_K_L14.5 GB 18.1 GB
Too big Get file →
IQ4_XS14.8 GB 18.4 GB
Too big Get file →
Q4_K_S15.7 GB 19.3 GB
Too big Get file →
Q3_K_XL15.9 GB 19.5 GB
Too big Get file →
Q4_K_M16.6 GB 20.2 GB
Too big Get file →
Q4_K_L18.0 GB 21.6 GB
Too big Get file →
Q5_K_S18.9 GB 22.5 GB
Too big Get file →
Q5_K_M19.4 GB 23.0 GB
Too big Get file →
Q5_K_L20.8 GB 24.4 GB
Too big Get file →
Q6_K22.3 GB 25.9 GB
Too big Get file →
Q6_K_L23.7 GB 27.3 GB
Too big Get file →
Q8_028.9 GB 32.5 GB
Too big Get file →
Q8_030.0 GB 33.6 GB
Too big Get file →
F32108.9 GB (3 parts) 112.5 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XS (8.4 GB file, ~12 GB memory). For 12‑GB VRAM, Q4_K_M (16.65 GB file, ~20.2 GB memory) is a good balance. For 32‑GB VRAM, Q8_0 (28.94 GB file, ~32.5 GB memory) offers full precision.

What GPU do you need for Tess-v2.5-Gemma-2-27B-alpha?

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: the best quant that fits is IQ2_XS (8.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (12.5 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (23.7 GB file, about 27.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (30.0 GB file, about 33.6 GB in use).

Which Tess-v2.5-Gemma-2-27B-alpha quant should you choose?

Q4_K_M is the usual starting point for Tess-v2.5-Gemma-2-27B-alpha: it balances file size and quality well. Here it is a 16.6 GB file.

The Q8_0 file is 28.9 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_XS at 8.4 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
Parameters27.2B
Layers46
Trained context8,192 tokens
KV cache (fp16)368 KB per token

Source

Quantized bybartowski
FamilyGemma
Licensegemma
Downloads (HF)481
Last updated2024-07-02

Frequently asked questions about Tess-v2.5-Gemma-2-27B-alpha

How much VRAM does Tess-v2.5-Gemma-2-27B-alpha need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 16.6 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 Tess-v2.5-Gemma-2-27B-alpha on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Tess-v2.5-Gemma-2-27B-alpha GGUF?

It depends on the quant: IQ2_XS is 8.4 GB, IQ2_S is 8.7 GB, IQ2_M is 9.4 GB, Q2_K is 10.4 GB, IQ3_XXS is 10.8 GB, IQ3_XS is 11.6 GB and 18 more.

What context length does Tess-v2.5-Gemma-2-27B-alpha support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.

Where can I download Tess-v2.5-Gemma-2-27B-alpha GGUF?

The files are on Hugging Face in the bartowski/Tess-v2.5-Gemma-2-27B-alpha-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 Tess-v2.5-Gemma-2-27B-alpha use?

Hugging Face lists the license as gemma. 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 Tess‑v2.5‑Gemma‑2‑27B‑alpha on 8 GB VRAM?

Yes, the IQ2_XS quantization (8.4 GB file) requires about 12 GB memory at 8k context, which fits within an 8 GB VRAM budget with some overhead.

Does this model support a system prompt?

No, the model does not support a system prompt according to the documentation.

What is the largest quantization available?

The largest quantization is Q8_0, 28.94 GB file with an estimated 32.5 GB memory usage at 8k context.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Gemma models

All Gemma →

Other medium models

All medium models →