---

license: apache-2.0

base_model: Qwen/Qwen3.5-9B

library_name: gguf

pipeline_tag: text-generation

tags:

- gguf

- tool-calling

- function-calling

- spike

language:

- en

- de

thumbnail: https://huggingface.co/Piecrust/Spike-9B-GGUF/resolve/main/banner.png

---

<p align="center">

<img src="https://huggingface.co/Piecrust/Spike-9B-GGUF/resolve/main/banner.png" alt="Spike-9B-GGUF" width="100%">

</p>

Spike-9B · GGUF

Spike is the assistant in the Spike AI iOS app. This is the largest Spike tool model — a server-class 9B for CPU/GPU serving via llama.cpp (a current build with qwen35 support).

📱 Get it on the App Store: https://apps.apple.com/app/spike-ai/id6749781844

A LoRA fine-tune of Qwen/Qwen3.5-9B (a vision-language

model), specialized for Spike's tool-calling — reminders, calendar, Apple Home, maps, web, files,

code, and the SSH/agent toolset — while staying a natural conversationalist. English + German.

Tool grammar: tool:<name> {json}.

Files

Spike-9B-Q4_K_M.gguf (≈5.3 GB) + Spike-9B-F16.gguf (≈17 GB source for requantizing).

> Qwen3.5 is a new hybrid (linear-attention + full-attention) architecture; an MLX build is also available for Apple silicon.

Eval — Spike harness (base Qwen3.5-9B → Spike-9B)

| Metric | Base | Spike-9B |

|---|---:|---:|

| Tool calls · thinking-off | 52.0% | 99.8% |

| Tool calls · thinking-on | — | 99.8% |

| Vision (image → tool / answer) | 72.5% | 100% |

| Normal-chat tool-leak (lower=better) | 1.6% | 0% |

Trained text+thinking+German, then a vision-replay stage, then a conversation-repair stage

(distilled base-model chat + contrastive tool/vision replay) so it keeps enable_thinking

reasoning and vision, tool-calls at 99.8%, and does not hijack casual chat into tool calls.

> The Vision row is the fine-tune's image → tool / answer ability, exposed by the MLX build; this GGUF is text-only (tools + thinking).

Usage

• Trained on Spike's compact system prompt; use that exact prompt.
• Optional reasoning via the enable_thinking chat-template kwarg.
• One text tool call per turn: tool:<name> {json}.

License

Derivative of Qwen3.5-9B under the Apache 2.0 License.