GE

Gemma-2-9B-It-SPPO-Iter3

GemmaGGUF by mradermacherUpdated 2024-10-20
Download on Hugging Face
Parameters9.24B
Context8K
Layers42
Architecturegemma2
Smallest quant2.4 GB
Quick answer

Gemma-2-9B-It-SPPO-Iter3 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 2.4 GB (IQ1_S) to 7.6 GB (Q6_K).

Gemma-2-9B-It-SPPO-Iter3 – 9.24B parameter GPT‑like model fine‑tuned with Self‑Play Preference Optimization

Gemma-2-9B-It-SPPO-Iter3 is a 9.24B parameter model based on the gemma2 architecture. It was fine‑tuned using Self‑Play Preference Optimization on synthetic datasets derived from the openbmb/UltraFeedback prompt sets. The model is primarily English and licensed under Apache‑2.0.

Good at

  • Fine‑tuned synthetic dialogue
  • Self‑play preference alignment
  • English language tasks

Limits

  • No vision support
  • Context limited to 8192 tokens
  • Requires 8k context memory estimates

Best for

  • Chatbot prototypes
  • Synthetic data generation
  • Fine‑tuned dialogue research

Who it’s for. Researchers and developers needing a GPT‑style model with alignment fine‑tuning. The model is suitable for applications that require high‑quality English dialogue generation within an 8192 token context window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 5.7 GB
Fits Get file →
IQ1_M2.5 GB 5.9 GB
Fits Get file →
IQ2_XXS2.8 GB 6.1 GB
Fits Get file →
IQ2_XS3.1 GB 6.4 GB
Fits Get file →
IQ2_S3.2 GB 6.5 GB
Fits Get file →
IQ2_M3.4 GB 6.8 GB
Fits Get file →
IQ3_XXS3.8 GB 7.1 GB
Fits Get file →
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_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 →
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 →

For 8GB VRAM use IQ1_S (2.38 GB, 5.7 GB memory) or IQ1_M (2.55 GB, 5.9 GB memory). For 12GB VRAM IQ2_S (3.21 GB, 6.5 GB memory) or Q2_K (3.81 GB, 7.1 GB memory). For 24GB VRAM Q4_K_M (5.76 GB, 9.1 GB memory) or Q5_K_M (6.65 GB, 10 GB memory).

What GPU do you need for Gemma-2-9B-It-SPPO-Iter3?

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: the best quant that fits is IQ1_M (2.5 GB file, about 5.9 GB in use).
  • 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).

Which Gemma-2-9B-It-SPPO-Iter3 quant should you choose?

Q4_K_M is the usual starting point for Gemma-2-9B-It-SPPO-Iter3: it balances file size and quality well. Here it is a 5.8 GB file.

If memory is tight, the smallest file is IQ1_S at 2.4 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 bymradermacher
FamilyGemma
Licensegemma
Downloads (HF)1,977
Last updated2024-10-20

Frequently asked questions about Gemma-2-9B-It-SPPO-Iter3

How much VRAM does Gemma-2-9B-It-SPPO-Iter3 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 Gemma-2-9B-It-SPPO-Iter3 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 Gemma-2-9B-It-SPPO-Iter3 GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.5 GB, IQ2_XXS is 2.8 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.2 GB, IQ2_M is 3.4 GB and 18 more.

What context length does Gemma-2-9B-It-SPPO-Iter3 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 Gemma-2-9B-It-SPPO-Iter3 GGUF?

The files are on Hugging Face in the mradermacher/Gemma-2-9B-It-SPPO-Iter3-i1-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 Gemma-2-9B-It-SPPO-Iter3 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 this model on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quant, which require about 5.7–5.9 GB of VRAM at 8k context.

Does this model support vision inputs?

No, the model has no vision capability.

What is the maximum context length?

The model supports up to 8192 tokens of context.

Other GGUFs of Gemma-2-9B-It-SPPO-Iter3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other small models

All small models →