GE

Gemma2 Nephilim v3 9B

GemmaGGUF by mradermacherUpdated 2024-08-09
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant3.8 GB
Quick answer

Gemma2 Nephilim v3 9B 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 (F16).

Gemma2 Nephilim v3 9B – 9.24B parameter language model

Gemma2 Nephilim v3 9B is a 9.24B parameter model merged from multiple Gemma-2 variants. It supports a 8192 token context window and is available in several GGUF quantizations. The model is suitable for creative text generation and roleplay tasks.

Good at

  • Creative text generation
  • Roleplay scenarios
  • Long context handling

Limits

  • No vision support
  • License is gemma
  • No mixture of experts

Best for

  • Chatbot development
  • Story writing
  • Code generation

Who it’s for. Developers and researchers needing a large Gemma model with flexible quantization options. The model is ideal for those who can manage the memory requirements of the larger quants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.8 GB 7.1 GB
Fits Get file →
IQ3_XS4.1 GB 7.5 GB
Tight Get file →
IQ3_S4.3 GB 7.7 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 →
Q4_K_S5.5 GB 8.8 GB
Too big Get file →
Q4_K_M5.8 GB 9.1 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 →
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 (file size 5.76 GB, estimated memory 9.1 GB). For 12 GB VRAM Q5_K_M (6.65 GB, 10 GB). For 16 GB VRAM Q6_K (7.59 GB, 10.9 GB).

What GPU do you need for Gemma2 Nephilim v3 9B?

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 (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 Gemma2 Nephilim v3 9B quant should you choose?

Q4_K_M is the usual starting point for Gemma2 Nephilim v3 9B: 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 bymradermacher
FamilyGemma
Licensegemma
Downloads (HF)619
Last updated2024-08-09

Frequently asked questions about Gemma2 Nephilim v3 9B

How much VRAM does Gemma2 Nephilim v3 9B 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 Gemma2 Nephilim v3 9B 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 Gemma2 Nephilim v3 9B GGUF?

It depends on the quant: Q2_K is 3.8 GB, IQ3_XS is 4.1 GB, IQ3_S is 4.3 GB, Q3_K_S is 4.3 GB, IQ3_M is 4.5 GB, Q3_K_M is 4.8 GB and 9 more.

What context length does Gemma2 Nephilim v3 9B 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 Gemma2 Nephilim v3 9B GGUF?

The files are on Hugging Face in the mradermacher/Gemma2-Nephilim-v3-9B-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 Gemma2 Nephilim v3 9B 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 Gemma2 Nephilim v3 9B on 8 GB VRAM?

Use the Q4_K_M quant; it requires about 9.1 GB of VRAM at 8k context, which is close to 8 GB but may need swapping.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is licensed under the gemma license.

Other GGUFs of Gemma2-Nephilim-v3-9B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other small models

All small models →