A frontier creative-writing model, distilled from GLM 5.2 into Qwen3-4B
Everything below lives in this one repository: pick the format that matches your runtime.
| Format | File / folder | Precision | Size | Works with |
|---|---|---|---|---|
| MLX | model.safetensors (repo root) |
4-bit (group size 64) | 2.26 GB | mlx-lm / MLX on Apple Silicon |
| GGUF | prism_creative_1_mini_Q4_K_M.gguf |
Q4_K_M (4-bit) | 2.50 GB | llama.cpp, Ollama, LM Studio |
Prism Creative 1 Mini is a compact creative-writing and storytelling model, fine-tuned via LoRA on Qwen3-4B-Instruct using a distilled dataset generated by GLM 5.2. It's built to write across genres, forms, and tones — short stories, character sketches, poetry, dialogue scenes, worldbuilding passages, flash fiction, and more — while staying immersive and avoiding the flat, generic "AI assistant" register.
Part of the Prism family of creative and roleplay models.
mlx-community/Qwen3-4B-Instruct-2507-4bitThe training data went through two hardening passes after an initial run surfaced two failure modes: a tendency to loop/repeat on very short fixed-length forms (like 100-word drabbles), and an over-reliance on a handful of "safe" cliché details (e.g. a clock reading a specific time) across otherwise-unrelated prompts. Both the generation prompt and an automated filter (rejecting outputs with excessive 4-gram repetition or flagged cliché phrases) were tightened before the final dataset was generated, and the existing data was re-filtered to match.
A held-out sanity check across flash fiction, worldbuilding, poetry, and dialogue produced coherent, well-formed, in-genre output with no leaked planning text and no repetition loops. Example (flash fiction, mystery noir, 100-word constraint):
Rain slicked the city like oil. I found her in the alley behind the pawn shop, fingers curled around a rusted key. "You knew," she whispered, eyes hollow...
This repo includes both:
| Format | File | Notes |
|---|---|---|
| MLX (4-bit) | model.safetensors + config |
For Apple Silicon via mlx-lm |
| GGUF (Q4_K_M) | prism_creative_1_mini_Q4_K_M.gguf |
For llama.cpp and compatible runtimes (LM Studio, Ollama, etc.) |
from mlx_lm import load, generate
model, tokenizer = load("VertexAIco/prism-creative-1-mini")
prompt = "Write a short story opening about a lighthouse keeper who receives a letter from someone who shouldn't exist."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
response = generate(model, tokenizer, prompt=text, max_tokens=400)
print(response)
llama-cli -hf VertexAIco/prism-creative-1-mini -m prism_creative_1_mini_Q4_K_M.gguf -p "Write a short story opening about a lighthouse keeper who receives a letter from someone who shouldn't exist."
For best results, use the system prompt the model was trained with:
You are a skilled creative writer capable of working across genres, forms, and tones. Follow the given writing prompt precisely -- respect any length, format, and style constraints exactly. Write only the requested creative piece: no preamble, no meta-commentary about your approach, no "Here's a story about..." framing. Begin directly with the piece itself.
This is a 4B-parameter model fine-tuned via LoRA on a moderately sized (2,500-example) dataset — it's capable but not infallible. It can still occasionally repeat itself on very constrained short forms, and like any distilled model it inherits some of its teacher's stylistic tendencies. Treat outputs as a strong first draft, not a final one.
Apache 2.0, inherited from the Qwen3 base model.
mlx-community/Qwen3-4B-Instruct-2507-4bit