Qwen3 30B A3B Instruct 2507 REAM Heretic needs about 15.5 GB of memory at Q4_K_M (a 14.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 0.1 GB to 19.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3 30B A3B Instruct 2507 REAM Heretic – a compressed 23.3B‑parameter MoE model
This model is a compressed version of Qwen3‑30B‑A3B‑Instruct‑2507, reducing experts from 128 to 96. It retains over 94 % of the original performance while cutting storage and GPU memory by roughly 25 %. The model is available in multiple GGUF quantizations.
Good at
- Large‑context reasoning up to 262144 tokens
- High‑quality instruction following
- Efficient MoE inference
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Chatbots needing long context
- Research prototyping with reduced GPU memory
- Fine‑tuning on custom datasets
Who it’s for. Developers and researchers who need a large‑parameter LLM with MoE efficiency and long‑context capability. The model is suitable for environments where GPU memory is limited but high performance is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 4.9 GB | 6.3 GB | Fits | Get file → | |
| IQ1_M | 5.4 GB | 6.8 GB | Fits | Get file → | |
| IQ2_XXS | 6.3 GB | 7.6 GB | Tight | Get file → | |
| IQ2_XS | 7.0 GB | 8.3 GB | Too big | Get file → | |
| IQ2_S | 7.1 GB | 8.4 GB | Too big | Get file → | |
| IQ2_M | 7.8 GB | 9.1 GB | Too big | Get file → | |
| Q2_K_S | 8.1 GB | 9.4 GB | Too big | Get file → | |
| Q2_K | 8.6 GB | 9.9 GB | Too big | Get file → | |
| IQ3_XXS | 9.1 GB | 10.4 GB | Too big | Get file → | |
| IQ3_XS | 9.6 GB | 10.9 GB | Too big | Get file → | |
| Q3_K_S | 10.2 GB | 11.5 GB | Too big | Get file → | |
| IQ3_S | 10.2 GB | 11.5 GB | Too big | Get file → | |
| IQ3_M | 10.3 GB | 11.7 GB | Too big | Get file → | |
| Q3_K_M | 11.2 GB | 12.6 GB | Too big | Get file → | |
| Q3_K_L | 12.2 GB | 13.5 GB | Too big | Get file → | |
| IQ4_XS | 12.5 GB | 13.8 GB | Too big | Get file → | |
| Q4_0 | 13.3 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_S | 13.3 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_M | 14.2 GB | 15.5 GB | Too big | Get file → | |
| Q4_1 | 14.7 GB | 16.0 GB | Too big | Get file → | |
| Q5_K_S | 16.1 GB | 17.4 GB | Too big | Get file → | |
| Q5_K_M | 16.6 GB | 17.9 GB | Too big | Get file → | |
| Q6_K | 19.1 GB | 20.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.95 GB, 6.3 GB memory at 8k context). For 12 GB VRAM, Q4_K_S (13.33 GB, 14.6 GB memory) or IQ4_XS (12.51 GB, 13.8 GB memory). For 20 GB VRAM, Q6_K (19.13 GB, 20.4 GB memory) offers the best trade‑off.
What GPU do you need for Qwen3 30B A3B Instruct 2507 REAM 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 the main file (0.1 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.4 GB in use).
- 8 GB VRAM: the best quant that fits is IQ2_XXS (6.3 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_M (10.3 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_1 (14.7 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (19.1 GB file, about 20.4 GB in use).
Which Qwen3 30B A3B Instruct 2507 REAM Heretic quant should you choose?
Q4_K_M is the usual starting point for Qwen3 30B A3B Instruct 2507 REAM Heretic: it balances file size and quality well. Here it is a 14.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 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
Frequently asked questions about Qwen3 30B A3B Instruct 2507 REAM Heretic
How much VRAM does Qwen3 30B A3B Instruct 2507 REAM Heretic need?
About 15.5 GB at Q4_K_M with an 8K context window. That is the 14.2 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 Qwen3 30B A3B Instruct 2507 REAM Heretic on an 8 GB GPU?
Yes, with IQ2_XXS: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 30B A3B Instruct 2507 REAM Heretic GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 4.9 GB, IQ1_M is 5.4 GB, IQ2_XXS is 6.3 GB, IQ2_XS is 7.0 GB, IQ2_S is 7.1 GB and 18 more.
What context length does Qwen3 30B A3B Instruct 2507 REAM 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 Qwen3 30B A3B Instruct 2507 REAM Heretic GGUF?
The files are on Hugging Face in the mradermacher/Qwen3-30B-A3B-Instruct-2507-REAM-heretic-i1-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 Qwen3 30B A3B Instruct 2507 REAM 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 this model on 8 GB VRAM?
Yes, using the IQ1_S quant which is 4.95 GB and requires about 6.3 GB of VRAM at 8k context.
Does this 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.