Ornith 1.5 35B A3B REAP 50 needs about 12.5 GB of memory at Q4_K_M (a 11.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 11.4 GB (Q4_K_M) to 19.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Ornith 1.5 35B A3B REAP 50 – 18.5B parameter MoE model
Ornith 1.5 35B A3B REAP 50 is a 18.5B parameter mixture‑of‑experts model based on the qwen35moe architecture. It activates about 3B parameters per token and is pruned to 50% with REAP. The model is released under the MIT license.
Good at
- Coding and agentic benchmarks
- Fast inference on CPU/Apple‑Silicon
- Large context support
Limits
- Requires recent llama.cpp with qwen35moe support
- No vision or audio capabilities
- Large VRAM needed for higher precision quants
Best for
- Developer tooling and code generation
- Agentic task execution
- Long‑form reasoning with 262144 token context
Who it’s for. Engineers and researchers needing a mid‑size MoE model with strong coding performance. The model is suitable for users with access to recent llama.cpp builds and sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 11.4 GB | 12.5 GB | Too big | Get file → | |
| Q5_K_M | 13.3 GB | 14.4 GB | Too big | Get file → | |
| Q6_K | 15.3 GB | 16.4 GB | Too big | Get file → | |
| Q8_0 | 19.7 GB | 20.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 11.37 GB, estimated 12.5 GB memory). If 12 GB VRAM is available, Q5_K_M (13.26 GB, 14.4 GB memory) is a good balance. For 16 GB VRAM, Q6_K (15.26 GB, 16.4 GB memory) or Q8_0 (19.75 GB, 20.9 GB memory) can be used, noting the higher memory requirement.
What GPU do you need for Ornith 1.5 35B A3B REAP 50?
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 Q5_K_M (13.3 GB file, about 14.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (19.7 GB file, about 20.9 GB in use).
Which Ornith 1.5 35B A3B REAP 50 quant should you choose?
Q4_K_M is the usual starting point for Ornith 1.5 35B A3B REAP 50: it balances file size and quality well. Here it is a 11.4 GB file.
The Q8_0 file is 19.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Ornith 1.5 35B A3B REAP 50
How much VRAM does Ornith 1.5 35B A3B REAP 50 need?
About 12.5 GB at Q4_K_M with an 8K context window. That is the 11.4 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 Ornith 1.5 35B A3B REAP 50 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Ornith 1.5 35B A3B REAP 50 GGUF?
It depends on the quant: Q4_K_M is 11.4 GB, Q5_K_M is 13.3 GB, Q6_K is 15.3 GB, Q8_0 is 19.7 GB.
What context length does Ornith 1.5 35B A3B REAP 50 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Ornith 1.5 35B A3B REAP 50 GGUF?
The files are on Hugging Face in the Ttimms/Ornith-1.5-35B-A3B-REAP-50-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 Ornith 1.5 35B A3B REAP 50 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 Ornith 1.5 35B A3B REAP 50 on 8 GB VRAM?
Yes, with the Q4_K_M quant the estimated VRAM usage is 12.5 GB, which is close to 8 GB but may require swapping or lower context.
Does this model support vision or audio?
No, the model has no vision or audio capabilities.
What is the context length of this model?
The trained context length is 262144 tokens.