QW

shirdel coder 9b claude fable 5

QwenGGUF by TesleumUpdated 2026-07-05
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant7.4 GB
Quick answer

shirdel coder 9b claude fable 5 needs about 8.9 GB of memory at Q6_K (a 7.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Shirdel Coder 9B Claude Fable 5 – a multimodal, coding‑focused LLM

Shirdel Coder 9B Claude Fable 5 is a Qwen3.5‑based model fine‑tuned with Claude Fable 5 instruction style and Evol‑Instruct‑Code‑80k‑v1. It supports coding, reasoning, tools, and vision tasks. The model is available in a Q6_K GGUF quantization.

Good at

  • Coding and code generation
  • Multimodal reasoning with vision
  • Tool‑using instruction following

Limits

  • Requires 8.9 GB VRAM at 8 k context
  • No explicit language list provided
  • Licensed under ecl‑2.0

Best for

  • Developers building code assistants
  • Researchers testing multimodal reasoning
  • Teams needing a 9 B parameter model with vision

Who it’s for. The model is suited for developers and researchers who need a 9 B parameter LLM that can handle code, reasoning, and vision tasks. It is ideal for projects that require instruction‑tuned behavior and multimodal input.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K7.4 GB 8.9 GB
Too big Get file →

The only available quantization is Q6_K, with a file size of 7.36 GB and an estimated memory usage of 8.9 GB at 8 k context. This is suitable for systems with at least 8 GB VRAM. No other quants are provided.

What GPU do you need for shirdel coder 9b claude fable 5?

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: the best quant that fits is Q6_K (7.4 GB file, about 8.9 GB in use).

Which shirdel coder 9b claude fable 5 quant should you choose?

Q6_K (7.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTesleum
FamilyQwen
Base modelQwen/Qwen3.5-9B
Licenseecl-2.0
Downloads (HF)862
Last updated2026-07-05

Frequently asked questions about shirdel coder 9b claude fable 5

How much VRAM does shirdel coder 9b claude fable 5 need?

About 8.9 GB at Q6_K with an 8K context window. That is the 7.4 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 shirdel coder 9b claude fable 5 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of shirdel coder 9b claude fable 5 GGUF?

It depends on the quant: Q6_K is 7.4 GB.

What context length does shirdel coder 9b claude fable 5 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download shirdel coder 9b claude fable 5 GGUF?

The files are on Hugging Face in the Tesleum/shirdel-coder-9b-claude-fable-5 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does shirdel coder 9b claude fable 5 use?

Hugging Face lists the license as ecl-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 Shirdel Coder 9B on 8 GB VRAM?

Yes, the Q6_K quantization requires approximately 8.9 GB VRAM at 8 k context, so an 8 GB GPU is borderline but may work with lower context sizes.

Does this model support vision tasks?

Yes, the model has detected vision ability and can be used with multimodal interfaces such as llama‑mtmd‑cli.

What license applies to this model?

The model is released under the ecl‑2.0 license.

Other GGUFs of Qwen3.5-9B

Similar models

Browse all →

More from Tesleum

All by Tesleum →

More Qwen models

All Qwen →

Other small models

All small models →