CL

Clemma 12B

ClemmaGGUF by ayan4m1Updated 2026-10-06
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant6.1 GB
Quick answer

Clemma 12B needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 6.1 GB (Q3_K_M) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Clemma 12B – a Gemma 4 12B finetuned for reasoning and tools

Clemma 12B is a 11.9‑billion parameter model based on Gemma 4. It was fine‑tuned with Opus 4.6 reasoning traces and supports reasoning, tools, and vision. The model is available in several GGUF quantizations.

Good at

  • Reasoning with structured prompts
  • Tool use and API calls
  • Vision tasks

Limits

  • No license information provided
  • No explicit vision limits but no dedicated vision model
  • Large context requires 262144 tokens

Best for

  • Chatbot assistants needing reasoning
  • Automated tool‑driven workflows
  • Image‑based question answering

Who it’s for. Developers and researchers who need a versatile 12B model for reasoning, tool integration, and vision tasks. The model is suitable for local deployment via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M6.1 GB 19.5 GB
Too big Get file →
Q4_K_M7.4 GB 20.8 GB
Too big Get file →
Q5_K_M8.5 GB 21.9 GB
Too big Get file →
Q6_K9.8 GB 23.2 GB
Too big Get file →
Q8_012.7 GB 26.1 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_M (6.09 GB, ~19.5 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (7.38 GB, ~20.8 GB). For 16 GB VRAM, Q5_K_M (8.55 GB, ~21.9 GB). Larger VRAM allows Q6_K or Q8_0.

What GPU do you need for Clemma 12B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).

Which Clemma 12B quant should you choose?

Q4_K_M is the usual starting point for Clemma 12B: it balances file size and quality well. Here it is a 7.4 GB file.

The Q8_0 file is 12.7 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 Q3_K_M at 6.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters11.9B
Layers48
Trained context262,144 tokens
KV cache (fp16)1536 KB per token

Source

Quantized byayan4m1
FamilyClemma
Downloads (HF)226
Last updated2026-10-06

Frequently asked questions about Clemma 12B

How much VRAM does Clemma 12B need?

About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 Clemma 12B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Clemma 12B GGUF?

It depends on the quant: Q3_K_M is 6.1 GB, Q4_K_M is 7.4 GB, Q5_K_M is 8.5 GB, Q6_K is 9.8 GB, Q8_0 is 12.7 GB.

What context length does Clemma 12B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.

Where can I download Clemma 12B GGUF?

The files are on Hugging Face in the ayan4m1/Clemma-12B-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 Clemma 12B on 8 GB VRAM?

Yes, the Q3_K_M quantization is 6.09 GB and requires about 19.5 GB of memory at 8k context.

Does Clemma 12B support vision tasks?

Yes, the model has detected vision ability, but it is not a dedicated vision model.

Similar models

Browse all →

More from ayan4m1

All by ayan4m1 →

More Clemma models

All Clemma →

Other medium models

All medium models →