Hemlock Qwen3 Coder REAP 25B A3B needs about 16.4 GB of memory at Q4_K_M (a 15.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 20.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Hemlock Qwen3 Coder REAP 25B A3B – a 24.9B parameter coding model
Hemlock Qwen3 Coder REAP 25B A3B is a 24.9B parameter model built on the Qwen3moe architecture. It is a mixture of experts with 3 active parameters and a trained context of 262144 tokens. The model focuses on coding and tool usage.
Good at
- Large context coding
- Tool integration
- Mixture of experts
Limits
- No vision support
- License not specified
- Requires large VRAM for higher quants
Best for
- Code generation
- Tool-assisted programming
- Long context debugging
Who it’s for. Developers and researchers needing a large‑context coding model. It is suitable for projects that can accommodate the memory demands of a 25B parameter mixture of experts model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 5.3 GB | 6.6 GB | Fits | Get file → | |
| IQ1_M | 5.8 GB | 7.1 GB | Fits | Get file → | |
| IQ2_XXS | 6.7 GB | 8.0 GB | Too big | Get file → | |
| IQ2_XS | 7.4 GB | 8.7 GB | Too big | Get file → | |
| IQ2_S | 7.6 GB | 8.9 GB | Too big | Get file → | |
| IQ2_M | 8.3 GB | 9.6 GB | Too big | Get file → | |
| Q2_K_S | 8.6 GB | 9.9 GB | Too big | Get file → | |
| Q2_K | 9.2 GB | 10.5 GB | Too big | Get file → | |
| IQ3_XXS | 9.7 GB | 11.0 GB | Too big | Get file → | |
| IQ3_XS | 10.3 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_S | 10.8 GB | 12.2 GB | Too big | Get file → | |
| IQ3_S | 10.9 GB | 12.2 GB | Too big | Get file → | |
| IQ3_M | 11.0 GB | 12.3 GB | Too big | Get file → | |
| Q3_K_M | 12.0 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_L | 13.0 GB | 14.3 GB | Too big | Get file → | |
| IQ4_XS | 13.4 GB | 14.7 GB | Too big | Get file → | |
| Q4_0 | 14.2 GB | 15.5 GB | Too big | Get file → | |
| Q4_K_S | 14.2 GB | 15.5 GB | Too big | Get file → | |
| Q4_K_M | 15.1 GB | 16.4 GB | Too big | Get file → | |
| Q4_1 | 15.6 GB | 16.9 GB | Too big | Get file → | |
| Q5_K_S | 17.2 GB | 18.5 GB | Too big | Get file → | |
| Q5_K_M | 17.7 GB | 19.0 GB | Too big | Get file → | |
| Q6_K | 20.4 GB | 21.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (5.27 GB file, 6.6 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (7.42 GB file, 8.7 GB memory). For 16 GB VRAM, Q4_K_M (15.12 GB file, 16.4 GB memory). Estimates are approximate.
What GPU do you need for Hemlock Qwen3 Coder REAP 25B A3B?
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 (6.7 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (10.3 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (14.2 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (20.4 GB file, about 21.7 GB in use).
Which Hemlock Qwen3 Coder REAP 25B A3B quant should you choose?
Q4_K_M is the usual starting point for Hemlock Qwen3 Coder REAP 25B A3B: it balances file size and quality well. Here it is a 15.1 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 Hemlock Qwen3 Coder REAP 25B A3B
How much VRAM does Hemlock Qwen3 Coder REAP 25B A3B need?
About 16.4 GB at Q4_K_M with an 8K context window. That is the 15.1 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 Hemlock Qwen3 Coder REAP 25B A3B on an 8 GB GPU?
Yes, with IQ2_XXS: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hemlock Qwen3 Coder REAP 25B A3B GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 5.3 GB, IQ1_M is 5.8 GB, IQ2_XXS is 6.7 GB, IQ2_XS is 7.4 GB, IQ2_S is 7.6 GB and 18 more.
What context length does Hemlock Qwen3 Coder REAP 25B A3B 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 Hemlock Qwen3 Coder REAP 25B A3B GGUF?
The files are on Hugging Face in the mradermacher/Hemlock-Qwen3-Coder-REAP-25B-A3B-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?
Yes, using the IQ1_S quant which requires about 6.6 GB memory at 8 k context.
Does this model support vision tasks?
No, the model has no vision capabilities.
What is the maximum context length?
The model was trained with a context of 262144 tokens.