fable coder 35B A3B needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 21.7 GB (Q4_K_M) to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
35B Mixture‑of‑Experts coding model with agentic behavior
fable coder 35B A3B is a 35.5B parameter model with ≈3B active experts. It is built on Qwen3.6‑35B‑A3B and fine‑tuned for agentic coding tasks. The model is released under Apache‑2.0 and supports native reasoning and tool‑use in a harness.
Good at
- Agentic coding with tool calls
- Native reasoning in Qwen chains
- Open‑weights model
Limits
- Requires 32GB VRAM at Q4/Q5
- No vision support
- Large context token limit of 262144
Best for
- Writing and editing code in an agent harness
- Running code tests iteratively
- Generating coding solutions with tool integration
Who it’s for. Developers and researchers needing an open‑source coding agent that can edit files and run tests. The model is suitable for projects that require agentic behavior without a proprietary license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → | |
| Q5_K_M | 25.3 GB | 26.5 GB | Too big | Get file → | |
| Q6_K | 29.2 GB | 30.4 GB | Too big | Get file → | |
| Q8_0 | 37.8 GB | 39.0 GB | Too big | Get file → |
For 32GB GPUs, use Q4_K_M (21.71 GB file, ~22.9 GB memory at 8k context) or Q5_K_M (25.35 GB file, ~26.5 GB memory). If you have a 48GB+ GPU, Q8_0 (37.8 GB file, ~39 GB memory) is available. Memory estimates are approximate.
What GPU do you need for fable coder 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 Q4_K_M (21.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).
Which fable coder 35B A3B quant should you choose?
Q4_K_M is the usual starting point for fable coder 35B A3B: it balances file size and quality well. Here it is a 21.7 GB file.
The Q8_0 file is 37.8 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 fable coder 35B A3B
How much VRAM does fable coder 35B A3B need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 fable coder 35B A3B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of fable coder 35B A3B GGUF?
It depends on the quant: Q4_K_M is 21.7 GB, Q5_K_M is 25.3 GB, Q6_K is 29.2 GB, Q8_0 is 37.8 GB.
What context length does fable coder 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 2.8 GB at 32K.
Where can I download fable coder 35B A3B GGUF?
The files are on Hugging Face in the Achilles1089/fable-coder-35B-A3B-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 fable coder 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.
Can I run fable coder 35B A3B on a 24GB GPU?
At Q4 or Q5 quantization it may fit with a short context, but 24GB is below the recommended 32GB for stable performance.
Does the model support vision or image inputs?
No, the model has no vision capability.
What license applies to this model?
The model is released under the Apache‑2.0 license.