MA

Mars 27B V.1 Heretic v1.2

MarsGGUF by mradermacherUpdated 2026-07-30
Download on Hugging Face
Parameters27B
Context128K
Layers62
Architecturegemma3
Smallest quant0.0 GB
Quick answer

Mars 27B V.1 Heretic v1.2 needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

Mars 27B V.1 Heretic v1.2 – 27B Gemini3 LLM

Mars 27B V.1 Heretic v1.2 is a 27B parameter Gemini3 model quantized for GGUF. It supports a 131072 token context window and focuses on zero refusals with low KL divergence. The model is available in multiple quantizations for varied memory budgets.

Good at

  • Large context reasoning
  • Low refusal rates
  • High token throughput

Limits

  • No vision support
  • License not specified
  • Requires high VRAM for full precision

Best for

  • Long‑form content generation
  • Complex dialogue systems
  • Research prototyping

Who it’s for. Engineers and researchers needing a large‑context LLM with minimal refusal behavior. Suitable for developers who can manage the memory requirements of a 27B parameter model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 4.7 GB
Fits Get file →
IQ1_S6.3 GB 10.9 GB
Too big Get file →
IQ1_M6.8 GB 11.5 GB
Too big Get file →
IQ2_XXS7.7 GB 12.3 GB
Too big Get file →
IQ2_XS8.4 GB 13.1 GB
Too big Get file →
IQ2_S8.8 GB 13.4 GB
Too big Get file →
IQ2_M9.5 GB 14.2 GB
Too big Get file →
Q2_K_S9.8 GB 14.4 GB
Too big Get file →
Q2_K10.5 GB 15.2 GB
Too big Get file →
IQ3_XXS10.7 GB 15.4 GB
Too big Get file →
IQ3_XS11.6 GB 16.2 GB
Too big Get file →
IQ3_S12.2 GB 16.8 GB
Too big Get file →
Q3_K_S12.2 GB 16.8 GB
Too big Get file →
IQ3_M12.5 GB 17.2 GB
Too big Get file →
Q3_K_M13.4 GB 18.1 GB
Too big Get file →
Q3_K_L14.5 GB 19.2 GB
Too big Get file →
IQ4_XS14.8 GB 19.4 GB
Too big Get file →
Q4_015.6 GB 20.3 GB
Too big Get file →
Q4_K_S15.7 GB 20.3 GB
Too big Get file →
Q4_K_M16.5 GB 21.2 GB
Too big Get file →
Q4_117.2 GB 21.8 GB
Too big Get file →
Q5_K_S18.8 GB 23.4 GB
Too big Get file →
Q5_K_M19.3 GB 23.9 GB
Too big Get file →
Q6_K22.2 GB 26.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (10.9 GB memory at 8k context) or IQ1_M (11.5 GB). For 12 GB VRAM, IQ2_XS (13.1 GB) or IQ2_S (13.4 GB) are suitable. For 16 GB VRAM, Q3_K_S (16.8 GB) or IQ3_S (16.8 GB) fit well. Memory estimates are approximate.

What GPU do you need for Mars 27B V.1 Heretic v1.2?

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 the main file (0.0 GB file, about 4.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_M (6.8 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (10.7 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).

Which Mars 27B V.1 Heretic v1.2 quant should you choose?

Q4_K_M is the usual starting point for Mars 27B V.1 Heretic v1.2: it balances file size and quality well. Here it is a 16.5 GB file.

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

Architecturegemma3
Parameters27B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized bymradermacher
FamilyMars
Downloads (HF)1,112
Last updated2026-07-30

Frequently asked questions about Mars 27B V.1 Heretic v1.2

How much VRAM does Mars 27B V.1 Heretic v1.2 need?

About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Mars 27B V.1 Heretic v1.2 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mars 27B V.1 Heretic v1.2 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 6.3 GB, IQ1_M is 6.8 GB, IQ2_XXS is 7.7 GB, IQ2_XS is 8.4 GB, IQ2_S is 8.8 GB and 18 more.

What context length does Mars 27B V.1 Heretic v1.2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download Mars 27B V.1 Heretic v1.2 GGUF?

The files are on Hugging Face in the mradermacher/Mars-27B-V.1-heretic-v1.2-i1-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 this model on 8 GB VRAM?

The smallest quant that fits is IQ1_S, which requires about 10.9 GB at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision?

No, the model is purely text; any vision files would be in a separate mmproj repository.

What is the context length?

The model supports 131072 tokens of context.

Other GGUFs of Mars-27B-V.1-heretic-v1.2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mars models

All Mars →

Other medium models

All medium models →