RN

Rnj 1 Instruct Heretic

RnjGGUF by ZuzeTtUpdated 2026-02-23
Download on Hugging Face
Parameters8.31B
Context32K
Layers32
Architecturegemma3
Smallest quant2.0 GB
Quick answer

Rnj 1 Instruct Heretic needs about 6.7 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 30 quants, from 2.0 GB (IQ1_S) to 33.2 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Rnj 1 Instruct Heretic – 8.31B parameter gemma3 model

Rnj 1 Instruct Heretic is an 8.31B parameter gemma3 model optimized for code, STEM, and tool‑calling. It is open‑weight and trained from scratch by Essential AI. The model supports a 32,768 token context window and is released under Apache‑2.0.

Good at

  • Code generation
  • Math and science reasoning
  • Tool‑calling

Limits

  • No vision support
  • Requires large VRAM for higher precision
  • No mixture of experts

Best for

  • Developers building code assistants
  • Researchers needing STEM reasoning
  • Tool‑integrated agents

Who it’s for. Engineers and researchers who need a versatile, open‑weight model for programming, scientific queries, and tool‑based workflows. The model is suitable for users with sufficient GPU memory to run higher‑precision quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.7 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M3.0 GB 4.6 GB
Fits Get file →
Q2_K3.3 GB 4.9 GB
Fits Get file →
IQ3_XXS3.4 GB 4.9 GB
Fits Get file →
IQ3_XS3.6 GB 5.2 GB
Fits Get file →
Q3_K_S3.8 GB 5.4 GB
Fits Get file →
IQ3_S3.8 GB 5.4 GB
Fits Get file →
IQ3_M3.9 GB 5.5 GB
Fits Get file →
Q3_K_M4.2 GB 5.8 GB
Fits Get file →
Q3_K_L4.5 GB 6.1 GB
Fits Get file →
IQ4_XS4.6 GB 6.2 GB
Fits Get file →
Q4_04.7 GB 6.3 GB
Fits Get file →
IQ4_NL4.8 GB 6.4 GB
Fits Get file →
Q4_04.8 GB 6.4 GB
Fits Get file →
Q4_K_S4.9 GB 6.4 GB
Fits Get file →
Q4_K5.1 GB 6.7 GB
Fits Get file →
Q4_K_M5.1 GB 6.7 GB
Fits Get file →
Q4_15.3 GB 6.9 GB
Fits Get file →
Q5_K_S5.8 GB 7.4 GB
Tight Get file →
Q5_05.8 GB 7.4 GB
Tight Get file →
Q5_K5.9 GB 7.5 GB
Tight Get file →
Q5_K_M5.9 GB 7.5 GB
Tight Get file →
Q5_16.3 GB 7.9 GB
Tight Get file →
Q6_K6.8 GB 8.4 GB
Too big Get file →
Q8_08.8 GB 10.4 GB
Too big Get file →
F3233.2 GB 34.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.01 GB, 3.6 GB memory at 8 k context) or IQ1_M (2.17 GB, 3.7 GB memory). If 12 GB VRAM is available, Q4_K_M (5.11 GB, 6.7 GB memory) offers better quality. For maximum fidelity, F32 (33.25 GB, 34.8 GB memory) requires high‑end hardware.

What GPU do you need for Rnj 1 Instruct Heretic?

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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.2 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.3 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (33.2 GB file, about 34.8 GB in use).

Which Rnj 1 Instruct Heretic quant should you choose?

Q4_K_M is the usual starting point for Rnj 1 Instruct Heretic: it balances file size and quality well. Here it is a 5.1 GB file.

The Q8_0 file is 8.8 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 IQ1_S at 2.0 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

Architecturegemma3
Parameters8.31B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byZuzeTt
FamilyRnj
Licenseapache-2.0
Downloads (HF)593
Last updated2026-02-23

Frequently asked questions about Rnj 1 Instruct Heretic

How much VRAM does Rnj 1 Instruct Heretic need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.1 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 Rnj 1 Instruct Heretic on an 8 GB GPU?

Yes, with Q5_1: the 6.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Rnj 1 Instruct Heretic GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.8 GB, IQ2_M is 3.0 GB and 24 more.

What context length does Rnj 1 Instruct Heretic support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Rnj 1 Instruct Heretic GGUF?

The files are on Hugging Face in the ZuzeTt/rnj-1-Instruct-Heretic-Imatrix-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 Rnj 1 Instruct Heretic 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 Rnj 1 Instruct Heretic on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which fit within 8 GB VRAM and use about 3.6–3.7 GB memory at 8 k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from ZuzeTt

All by ZuzeTt →

More Rnj models

All Rnj →

Other small models

All small models →