heretic1 needs about 20.7 GB of memory at Q4_K_M (a 18.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 11.7 GB (IQ2_M) to 30.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
27B Qwen model fine‑tuned for efficient reasoning and coding
Heretic1 is a 27B‑parameter Qwen model fine‑tuned for coding, reasoning, roleplay and vision. It supports a 262144‑token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Coding and code generation
- Complex reasoning tasks
- Vision‑enabled prompts
Limits
- Large VRAM required for higher‑bit quantizations
- No explicit vision support in the base model
- License requires compliance with Apache‑2.0
Best for
- Developers building lightweight inference pipelines
- Researchers testing large‑context reasoning
- Applications needing multi‑modal prompts
Who it’s for. Engineers and researchers who need a 27B Qwen model with extensive context and multi‑modal capabilities. The model is suitable for local deployment on consumer hardware with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 11.7 GB | 14.3 GB | Too big | Get file → | |
| IQ2_M | 12.1 GB | 14.8 GB | Too big | Get file → | |
| IQ3_M | 14.1 GB | 16.7 GB | Too big | Get file → | |
| IQ3_M | 14.5 GB | 17.2 GB | Too big | Get file → | |
| IQ4_XS | 15.3 GB | 18.0 GB | Too big | Get file → | |
| IQ4_XS | 16.6 GB | 19.2 GB | Too big | Get file → | |
| IQ4_XS | 17.0 GB | 19.7 GB | Too big | Get file → | |
| Q4_K_S | 17.1 GB | 19.7 GB | Too big | Get file → | |
| Q4_K_S | 17.5 GB | 20.2 GB | Too big | Get file → | |
| Q4_K_M | 18.0 GB | 20.7 GB | Too big | Get file → | |
| Q4_K_M | 18.5 GB | 21.1 GB | Too big | Get file → | |
| Q5_K_S | 20.2 GB | 22.8 GB | Too big | Get file → | |
| Q5_K_S | 20.6 GB | 23.3 GB | Too big | Get file → | |
| Q5_K_M | 20.7 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_M | 21.2 GB | 23.8 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → | |
| Q6_K | 23.6 GB | 26.2 GB | Too big | Get file → | |
| Q6_K | 24.0 GB | 26.7 GB | Too big | Get file → | |
| Q8_0 | 29.8 GB | 32.4 GB | Too big | Get file → | |
| Q8_0 | 30.2 GB | 32.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_M (file size 11.67 GB, estimated 14.3 GB memory at 8 k context). For 12 GB VRAM, IQ3_M (14.08 GB, 16.7 GB memory). For 16 GB VRAM, Q4_K_M (18.05 GB, 20.7 GB memory). Higher‑bit quants require more VRAM.
What GPU do you need for heretic1?
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 IQ2_M (12.1 GB file, about 14.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (21.2 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (24.0 GB file, about 26.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (30.2 GB file, about 32.9 GB in use).
Which heretic1 quant should you choose?
Q4_K_M is the usual starting point for heretic1: it balances file size and quality well. Here it is a 18.0 GB file.
The Q8_0 file is 29.8 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 IQ2_M at 11.7 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
Source
Frequently asked questions about heretic1
How much VRAM does heretic1 need?
About 20.7 GB at Q4_K_M with an 8K context window. That is the 18.0 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 heretic1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of heretic1 GGUF?
It depends on the quant: IQ2_M is 11.7 GB, IQ2_M is 12.1 GB, IQ3_M is 14.1 GB, IQ3_M is 14.5 GB, IQ4_XS is 15.3 GB, IQ4_XS is 16.6 GB and 14 more.
What context length does heretic1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download heretic1 GGUF?
The files are on Hugging Face in the briancollet/heretic1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does heretic1 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 Heretic1 on 8 GB VRAM?
Use the IQ2_M quant; it requires about 14.3 GB memory at 8 k context, so 8 GB VRAM is insufficient for inference.
Does Heretic1 support vision tasks?
The model has detected vision ability, but no explicit vision support is listed; use with caution.
What license applies to Heretic1?
Heretic1 is released under the Apache‑2.0 license, requiring compliance with its terms.