GE

Gemma 4 12B It Esper4

GemmaGGUF by bartowskiUpdated 2026-07-20
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Gemma 4 12B It Esper4 needs about 21.0 GB of memory at Q4_K_M (a 7.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 26 quants, from 0.0 GB to 23.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

Gemma 4 12B It Esper4 – a 12B coding and reasoning model

Gemma 4 12B It Esper4 is a 11.9B parameter model optimized for coding, reasoning, and vision tasks. It supports a 262144 token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations for different memory budgets.

Good at

  • Coding tasks
  • Reasoning queries
  • Vision processing

Limits

  • No vision support in some quantizations
  • Large context requires significant VRAM
  • License is Apache‑2.0

Best for

  • Local code generation
  • Complex reasoning prompts
  • Vision‑enabled inference

Who it’s for. Developers and researchers who need a versatile 12B model for coding, reasoning, and vision. The model runs on local hardware with sufficient VRAM and supports llama.cpp and other GGUF‑compatible tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 13.4 GB
Too big Get file →
IQ2_S4.7 GB 18.1 GB
Too big Get file →
IQ2_M4.9 GB 18.3 GB
Too big Get file →
Q2_K5.1 GB 18.5 GB
Too big Get file →
IQ3_XXS5.1 GB 18.5 GB
Too big Get file →
Q2_K_L5.3 GB 18.7 GB
Too big Get file →
IQ3_XS5.5 GB 18.9 GB
Too big Get file →
Q3_K_S5.7 GB 19.1 GB
Too big Get file →
IQ3_M6.0 GB 19.4 GB
Too big Get file →
Q3_K_M6.3 GB 19.7 GB
Too big Get file →
Q3_K_L6.7 GB 20.0 GB
Too big Get file →
IQ4_XS6.8 GB 20.2 GB
Too big Get file →
Q3_K_XL6.9 GB 20.3 GB
Too big Get file →
IQ4_NL7.1 GB 20.5 GB
Too big Get file →
Q4_07.1 GB 20.5 GB
Too big Get file →
Q4_K_S7.2 GB 20.6 GB
Too big Get file →
Q4_K_M7.7 GB 21.0 GB
Too big Get file →
Q4_17.8 GB 21.1 GB
Too big Get file →
Q4_K_L7.9 GB 21.3 GB
Too big Get file →
Q5_K_S8.4 GB 21.8 GB
Too big Get file →
Q5_K_M8.8 GB 22.2 GB
Too big Get file →
Q5_K_L9.0 GB 22.4 GB
Too big Get file →
Q6_K10.2 GB 23.6 GB
Too big Get file →
Q6_K_L10.5 GB 23.9 GB
Too big Get file →
Q8_012.7 GB 26.1 GB
Too big Get file →
BF1623.8 GB 37.2 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (file size 7.66 GB, memory 21 GB). For 12‑GB VRAM, Q5_K_M (8.77 GB, 22.2 GB) or Q6_K (10.24 GB, 23.6 GB). For larger budgets, Q8_0 (12.67 GB, 26.1 GB) or BF16 (23.83 GB, 37.2 GB) provide higher quality.

What GPU do you need for Gemma 4 12B It Esper4?

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: the best quant that fits is the main file (0.0 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_L (10.5 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (23.8 GB file, about 37.2 GB in use).

Which Gemma 4 12B It Esper4 quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 12B It Esper4: it balances file size and quality well. Here it is a 7.7 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

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 bybartowski
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,942
Last updated2026-07-20

Frequently asked questions about Gemma 4 12B It Esper4

How much VRAM does Gemma 4 12B It Esper4 need?

About 21.0 GB at Q4_K_M with an 8K context window. That is the 7.7 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 It Esper4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 4 12B It Esper4 GGUF?

It depends on the quant: file is 0.0 GB, IQ2_S is 4.7 GB, IQ2_M is 4.9 GB, Q2_K is 5.1 GB, IQ3_XXS is 5.1 GB, Q2_K_L is 5.3 GB and 20 more.

What context length does Gemma 4 12B It Esper4 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 It Esper4 GGUF?

The files are on Hugging Face in the bartowski/ValiantLabs_gemma-4-12B-it-Esper4-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 It Esper4 use?

Hugging Face lists the license as apache-2.0. 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 Gemma 4 12B It Esper4 on 8 GB VRAM?

Use the Q4_K_M quantization; it requires about 21 GB VRAM at 8k context, so 8 GB VRAM is insufficient.

Does the model support vision tasks?

Yes, the model has detected vision ability, but some quantizations may not include vision weights.

Other GGUFs of gemma-4-12B-it-Esper4

Similar models

Browse all →

More from bartowski

All by bartowski →

More Gemma models

All Gemma →

Other medium models

All medium models →