Anansi 35B A3B needs about 20.0 GB of memory at IQ4_XS (a 18.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 16.9 GB (Q3_K_M) to 28.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Anansi 35B A3B – a 34.7B parameter Qwen35MOE model with 3B active experts
Anansi 35B A3B is a mixture‑of‑experts model based on the qwen35moe architecture. It contains 34.7B parameters with 3B active parameters per token. The model supports 262144 context tokens and is licensed under apache‑2.0.
Good at
- reasoning
- roleplay
- tools
Limits
- no vision support
- trained on 262144 tokens
- requires large VRAM for dense quant
Best for
- long‑form narrative generation
- instruction following
- prose refinement
Who it’s for. Developers and researchers needing a large‑scale language model that balances instruction following, narrative reasoning, and prose style. The model is suitable for systems with moderate GPU memory, such as 8‑GB GPUs, when using lower‑precision quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 16.9 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_M | 16.9 GB | 18.1 GB | Too big | Get file → | |
| IQ4_XS | 18.9 GB | 20.0 GB | Too big | Get file → | |
| IQ4_XS | 18.9 GB | 20.0 GB | Too big | Get file → | |
| Q6_K | 28.6 GB | 29.8 GB | Too big | Get file → | |
| Q6_K | 28.6 GB | 29.8 GB | Too big | Get file → |
For 8‑GB VRAM use Q3_K_M (file size 16.89 GB, estimated 18.1 GB at 8k context). If more memory is available, IQ4_XS (file size 18.85 GB, estimated 20 GB) offers higher quality. For maximum quality with sufficient VRAM, Q6_K (file size 28.64 GB, estimated 29.8 GB) is recommended.
What GPU do you need for Anansi 35B 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: 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: the best quant that fits is IQ4_XS (18.9 GB file, about 20.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.6 GB file, about 29.8 GB in use).
Which Anansi 35B A3B quant should you choose?
IQ4_XS (18.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q3_K_M at 16.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Anansi 35B A3B
How much VRAM does Anansi 35B A3B need?
About 20.0 GB at IQ4_XS with an 8K context window. That is the 18.9 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 Anansi 35B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Anansi 35B A3B GGUF?
It depends on the quant: Q3_K_M is 16.9 GB, Q3_K_M is 16.9 GB, IQ4_XS is 18.9 GB, IQ4_XS is 18.9 GB, Q6_K is 28.6 GB, Q6_K is 28.6 GB.
What context length does Anansi 35B 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 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Anansi 35B A3B GGUF?
The files are on Hugging Face in the BlueNipples/Anansi-35B-A3B-Q8-Prose-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 Anansi 35B A3B 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.
What license applies to this model?
The model is released under the apache‑2.0 license.
Does this model support image inputs?
No, Anansi 35B A3B does not have vision capabilities.