SP

Spikingkiki 27b

SpikingkikiGGUF by mradermacherUpdated 2026-05-12
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Spikingkiki 27b needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Spikingkiki 27b – a 27B‑parameter Qwen3.5 variant with spiking neurons

Spikingkiki 27b is a 26.9 billion‑parameter model based on the Qwen3.5 architecture. It replaces standard activations in attention and FFN layers with Leaky Integrate‑and‑Fire neurons for research into energy‑efficient inference. The model is released under the apache‑2.0 license.

Good at

  • reasoning
  • tools usage
  • spiking‑neuron research

Limits

  • no vision support
  • trained context 262144 tokens
  • not benchmarked end‑to‑end

Best for

  • research on spiking neural networks
  • energy‑efficient inference studies
  • testing LIF neuron behavior

Who it’s for. Researchers and developers interested in biologically inspired sparse activation. The model is suitable for academic experiments rather than production use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.1 GB 9.8 GB
Too big Get file →
IQ1_M7.6 GB 10.3 GB
Too big Get file →
IQ2_XXS8.4 GB 11.1 GB
Too big Get file →
IQ2_XS9.1 GB 11.7 GB
Too big Get file →
IQ2_S9.4 GB 12.0 GB
Too big Get file →
IQ2_M10.0 GB 12.7 GB
Too big Get file →
Q2_K_S10.2 GB 12.9 GB
Too big Get file →
Q2_K10.7 GB 13.4 GB
Too big Get file →
IQ3_XXS11.2 GB 13.8 GB
Too big Get file →
IQ3_XS12.0 GB 14.6 GB
Too big Get file →
Q3_K_S12.1 GB 14.7 GB
Too big Get file →
IQ3_S12.4 GB 15.1 GB
Too big Get file →
IQ3_M12.6 GB 15.2 GB
Too big Get file →
Q3_K_M13.3 GB 15.9 GB
Too big Get file →
Q3_K_L14.3 GB 17.0 GB
Too big Get file →
IQ4_XS15.1 GB 17.7 GB
Too big Get file →
Q4_015.5 GB 18.2 GB
Too big Get file →
Q4_K_S15.6 GB 18.2 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q4_117.1 GB 19.7 GB
Too big Get file →
Q5_K_S18.7 GB 21.3 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.15 GB file, 9.8 GB memory) or IQ1_M (7.63 GB file, 10.3 GB memory). If 12 GB VRAM is available, Q4_K_M (16.55 GB file, 19.2 GB memory) offers higher quality. Larger VRAM allows Q5_K_M or Q6_K for best performance.

What GPU do you need for Spikingkiki 27b?

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 (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_S (9.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.1 GB file, about 24.7 GB in use).

Which Spikingkiki 27b quant should you choose?

Q4_K_M is the usual starting point for Spikingkiki 27b: it balances file size and quality well. Here it is a 16.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)800
Last updated2026-05-12

Frequently asked questions about Spikingkiki 27b

How much VRAM does Spikingkiki 27b need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Spikingkiki 27b on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Spikingkiki 27b GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.1 GB, IQ1_M is 7.6 GB, IQ2_XXS is 8.4 GB, IQ2_XS is 9.1 GB, IQ2_S is 9.4 GB and 18 more.

What context length does Spikingkiki 27b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Spikingkiki 27b GGUF?

The files are on Hugging Face in the mradermacher/spikingkiki-27b-i1-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 Spikingkiki 27b 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 Spikingkiki 27b on 8 GB VRAM?

Use the IQ1_S or IQ1_M quant; they require about 9.8–10.3 GB memory at 8 k context.

Does this model support vision tasks?

No, it is a text‑only model; vision support is not included.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of spikingkiki-27b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Spikingkiki models

All Spikingkiki →

Other medium models

All medium models →