MiroThinker v1.5 30B Heretic needs about 33.8 GB of memory at Q8_0 (a 32.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
MiroThinker v1.5 30B Heretic – large‑context LLM with reduced refusals
MiroThinker v1.5 30B Heretic is a 30.5‑billion‑parameter mixture‑of‑experts model based on the qwen3moe architecture. It was abliterated with Heretic to lower refusal rates while keeping quality. The model supports a 262144‑token context window.
Good at
- Large context handling
- Low refusal rate
- High‑quality responses
Limits
- Requires 33.8 GB VRAM at 8 k context
- No vision support
- MIT license only
Best for
- Long‑form content creation
- Research summarization
- Code generation
Who it’s for. Developers and researchers needing a high‑capacity language model for extended conversations or document generation. The model is suitable for local deployment via llama.cpp on systems with ample VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 32.5 GB | 33.8 GB | Too big | Get file → |
The only available quant is Q8_0, file size 32.48 GB. It requires approximately 33.8 GB VRAM at 8 k context. If your GPU has at least 34 GB VRAM, Q8_0 is recommended. No other quants are provided.
What GPU do you need for MiroThinker v1.5 30B 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: 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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q8_0 (32.5 GB file, about 33.8 GB in use).
Which MiroThinker v1.5 30B Heretic quant should you choose?
Q8_0 (32.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiroThinker v1.5 30B Heretic
How much VRAM does MiroThinker v1.5 30B Heretic need?
About 33.8 GB at Q8_0 with an 8K context window. That is the 32.5 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 MiroThinker v1.5 30B Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 33.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MiroThinker v1.5 30B Heretic GGUF?
It depends on the quant: Q8_0 is 32.5 GB.
What context length does MiroThinker v1.5 30B Heretic support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.
Where can I download MiroThinker v1.5 30B Heretic GGUF?
The files are on Hugging Face in the jarradh/MiroThinker-v1.5-30B-heretic-Q8_0-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 MiroThinker v1.5 30B Heretic use?
Hugging Face lists the license as mit. 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?
No. The Q8_0 quant requires about 33.8 GB VRAM at 8 k context, so 8 GB is insufficient.
Does this model support image input?
No. The model has no vision capabilities.
What license applies to this model?
The model is released under the MIT license.