GE

gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated

GemmaGGUF by tplsUpdated 2026-06-26
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant7.3 GB
Quick answer

gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated needs about 22.0 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 7.3 GB (Q3_K_M) to 13.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Gemma-4 12B Coder – SFT v5 + abliterated, uncensored, tool‑calling ready

Gemma-4 12B Coder is a 11.9 billion‑parameter model fine‑tuned with SFT v5 and an abliteration guard. It supports coding and tool‑calling and is available in multiple GGUF quantizations for local deployment. The model is uncensored and requires a recovery shim for tool‑calling with llama.cpp.

Good at

  • Coding tasks
  • Tool‑calling with shim
  • Uncensored content

Limits

  • No vision support
  • Requires tool‑calling shim
  • Large context only 262144 tokens

Best for

  • Local code generation
  • Agentic tool use
  • Fine‑tuning with safetensors

Who it’s for. Developers and researchers who need a local, uncensored coding model with tool‑calling capability. The model is suitable for building agents that interact with APIs or other tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M7.3 GB 20.7 GB
Too big Get file →
IQ4_XS7.8 GB 21.2 GB
Too big Get file →
Q4_K_M8.6 GB 22.0 GB
Too big Get file →
Q5_K_M9.7 GB 23.1 GB
Too big Get file →
Q6_K11.0 GB 24.4 GB
Too big Get file →
Q8_013.6 GB 27.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (8.57 GB file, ~22 GB RAM). For 12 GB VRAM, Q5_K_M (9.73 GB file, ~23.1 GB RAM). For 16 GB VRAM, Q6_K (10.97 GB file, ~24.4 GB RAM).

What GPU do you need for gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated?

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 Q5_K_M (9.7 GB file, about 23.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (13.6 GB file, about 27.0 GB in use).

Which gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated quant should you choose?

Q4_K_M is the usual starting point for gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 13.6 GB, about 1.6 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 7.3 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

Frequently asked questions about gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated

How much VRAM does gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated need?

About 22.0 GB at Q4_K_M with an 8K context window. That is the 8.6 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 gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated GGUF?

It depends on the quant: Q3_K_M is 7.3 GB, IQ4_XS is 7.8 GB, Q4_K_M is 8.6 GB, Q5_K_M is 9.7 GB, Q6_K is 11.0 GB, Q8_0 is 13.6 GB.

What context length does gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated 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 gemma 4 12B coder fable5 composer2.5 v1 sft v5 abliterated GGUF?

The files are on Hugging Face in the tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-abliterated-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 4 12B coder fable5 composer2.5 v1 sft v5 abliterated 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, with the Q4_K_M quantization which requires about 22 GB of RAM at 8k context.

Does it support vision?

No, the model has no vision capability.

Do I need a tool‑calling shim?

Yes, llama.cpp under‑parses gemma‑4 native tool markup; use the provided shim to recover standard tool_calls.

Similar models

Browse all →

More from tpls

All by tpls →

More Gemma models

All Gemma →

Other medium models

All medium models →