amandoti/cluemaster-1.0

Cluemaster 1.0

A 3B Codenames spymaster. It reads a board and the clues so far, and answers with a short brainstorm, then a clue, a number and the target words.

• Base model: Ministral 3 3B Instruct, LoRA fine-tuned (rank 16, alpha 32, all attention and MLP layers).
• Format: GGUF, Q4_K_M, 2.1 GB.
• Runs in: Ollama, llama.cpp, LM Studio. About 3 GB of free memory; a 6 GB graphics card runs it fully on the GPU.

Results

Cluebench v1.0. Every clue was rated good, ok or bad in a blind rating, on held-out boards sealed before training. Every model got the same board and format, one answer at temperature 0. Cluemaster was benchmarked as the Q4_K_M file. The leader of each column is in bold.

Overall

Model	Cluebench	Rated good	Acceptable	Legal first try	Illegal	Invalid	Seconds per board	Tokens per answer
Cluemaster 1.0	60%	44%	68%	96%	4%	0%	2.5 s	93
Phi-4 Mini 3.8B	20%	17%	34%	63%	37%	1%	1.4 s	33
Granite 4.1 3B	20%	12%	33%	76%	24%	2%	0.6 s	19
Ministral 3 3B	5%	5%	19%	61%	39%	6%	2.8 s	53
Qwen 3.5 4B	3%	13%	17%	25%	75%	0%	1.9 s	29

Acceptable is legal and rated good or ok. Illegal is a clue that breaks a rule. Invalid is a legal clue aimed at a neutral or opponent word.

Fresh boards

Model	Score	Good	Acceptable	Illegal
Cluemaster 1.0	72	45%	85%	5%
Phi-4 Mini 3.8B	33	32%	47%	37%
Granite 4.1 3B	22	12%	37%	25%
Ministral 3 3B	7	8%	23%	45%
Qwen 3.5 4B	0	2%	5%	90%

Midgame (4 or more of your words left)

Model	Score	Good	Acceptable	Illegal
Cluemaster 1.0	40	32%	45%	5%
Phi-4 Mini 3.8B	11	5%	27%	36%
Granite 4.1 3B	16	9%	27%	23%
Ministral 3 3B	3	0%	14%	27%
Qwen 3.5 4B	9	23%	27%	68%

Endgame (3 or fewer of your words left)

Model	Score	Good	Acceptable	Illegal
Cluemaster 1.0	67	54%	74%	3%
Phi-4 Mini 3.8B	16	16%	29%	38%
Granite 4.1 3B	23	16%	34%	24%
Ministral 3 3B	5	7%	19%	38%
Qwen 3.5 4B	1	15%	18%	65%

Scoring

Clue	Points on its board
Good	100
Ok	70
Bad, or no clue	0
Invalid: a target is a neutral word	−10
Invalid: a target is an opponent word	−15
Illegal, whatever it was rated	−25

A segment scores 50% legal, 30% good and 20% acceptable, minus the penalties, never below zero. Cluebench is the mean of the three segments.

Use with Ollama

Put cluemaster-1.0-Q4_K_M.gguf and this Modelfile in one folder, then run ollama create cluemaster -f Modelfile.

FROM ./cluemaster-1.0-Q4_K_M.gguf
TEMPLATE """{{ if .System }}<s>[SYSTEM_PROMPT]{{ .System }}[/SYSTEM_PROMPT]{{ end }}{{ if .Prompt }}[INST]{{ .Prompt }}[/INST]{{ end }}{{ .Response }}</s>"""
PARAMETER stop <s>
PARAMETER stop [INST]
PARAMETER temperature 0.3
PARAMETER num_ctx 4096

For a full game with clue checks, use Cluemaster Studio: https://amandoti.win/cluemaster/studio.html

How to use it

The easy way: use Cluemaster Studio. Type in the board, press Get clue, and it handles the prompt and checks the clue against the rules.

Running it yourself: Cluemaster isn't a chat model. It does one job: you give it a board, and it gives you a clue.

Recommended system message:

You are a Codenames spymaster. Your teammate can see every word on the board but does not know which ones are yours. You give a one-word clue and a number: the number is how many of your team's words the clue points to.

The clue must not be a word on the board, or a form or part of one. Avoid clues that could lead your teammate to the opponent's words, the neutral words, or the assassin.

Recommended user message (put your own words in capitals):

BOARD
My team: BUNK, CENTER, BAND, SNAKE
Opponent: MAKEUP
Neutral: WELL, KITCHEN, STATE, HORSE
Assassin: MICROWAVE

Give a clue that connects 1 to 4 of your team's words. Connect 2 or 3 when there is a real link between them. If the words you have left have no good link, give a clue for a single word instead of forcing a weak pair.

Reply with your clue, the number, and the team words it connects, like this:
Clue: <one word>
Number: <how many team words it connects>
Words: <those team words, separated by commas>

What you get back:

Brainstorm:
- RUBBER: BAND, SNAKE. Found 2 of 2. Risk: WELL (neutral).
Clue: RUBBER
Number: 2
Words: BAND, SNAKE

Use the Clue, Number and Words lines. The brainstorm above them is its working. Set the temperature to about 0.3 and stop after 400 tokens, because it can keep writing extra answers after the first.

It only gives clues, so any other message gets a clue back.

Limits

• Midgame boards (4 or more of your words left) are its weakest case.
• About 4% of single answers are illegal, mostly by being or containing a board word. The Studio filters these out.
• Trained to give clues, not to guess. English only.

License

Apache 2.0, the same as the base model. This is a derivative of Ministral 3 3B Instruct by Mistral AI.