Mapika/Decider 0.8B

• License: Apache-2.0
• Release date: Not documented in the original card; 2026-09-19 is the first HF publication (repository creation).
• Modalities: Input: text; Output: typed decisions (choice, score, noul)
• Original model: Mapika/decider-0.8b

Description

The smallest Decider reads a state and typed questions, returning probabilities over supplied options without generating text. It is fine-tuned from Qwen3.5-0.8B-Base for routing, classification, yes/no judgments and short-state lookups, with less knowledge capacity than the larger Decider models.

Run

self serve decider:0.8b

Here is a link to the API docs: Decision API.

Example Request

With the server running, open another terminal and send a request:

curl http://localhost:8080/v1/systemone \
	-H 'Content-Type: application/json' \
	-d '{
		"state": "I was charged twice for the same order.",
		"questions": {
			"department": {
				"type": "choice",
				"instructions": "Which department should handle this support ticket?",
				"criteria": {
					"billing": "Payments and refunds",
					"technical": "Technical problems"
				}
			}
		}
	}'

The server returns a JSON decision for the department question.

Engine Parameters

Served by the llama.cpp-based ggmlc-custom-decider engine and adapter. These are startup settings, not per-request API fields.

Parameter	Default	What it controls
context_size	8192	Context tokens including the prompt; accepts integers from 512 to 262144.
threads	llama.cpp default	CPU workers; accepts integers from 1 to 1024.
temperature	1.0	Softmax temperature on option-letter logits, not text sampling; accepts 0.01 to 100.
gpu_layers	-1 (all); 0 on CPU devices	Layers offloaded to the GPU; accepts integers from -1 to 10000.
flash_attn	auto	Flash attention mode: auto, on, or off.
image_min_tokens	Unset (projector metadata)	Minimum image tokens, 1 to 65536; no effect on this text-only model.
image_max_tokens	Unset (projector metadata)	Maximum image tokens, 1 to 65536; no effect on this text-only model.

Override startup settings with --set <parameter>=<value>.

Quantizations and Files

Default variant: q4. Sizes and SHA-256 hashes are pinned in the model registry.

q4 (default)

File	Role	Size	SHA-256	Origin
decider-0.8b.Q4_K_M.gguf	model	504.8 MiB (529297856 bytes)	ce48f94d8f176e6433dc09ee34fd4a39ac16b29043beaeb7b81d98373b27cd67	mradermacher/decider-0.8b-GGUF

Total download: 504.8 MiB (529297856 bytes).

q8

File	Role	Size	SHA-256	Origin
decider-0.8b.Q8_0.gguf	model	774.2 MiB (811844032 bytes)	2665d08c1052b4e01dabcb08771d25579f6776f7066355e4a0ccc5f74e32d4a2	mradermacher/decider-0.8b-GGUF

Total download: 774.2 MiB (811844032 bytes).

Notes

• Text only; up to 10 options per question in this engine, even though upstream supports larger option sets.
• English-focused, with no reasoning generation; complex rules in questions are not followed reliably. Prefer plain questions and described options.
• The engine uses the registry temperature of 1.0, not the original card's fitted 1.03; validate confidence on your own data.
• Download size is not the total runtime memory requirement.
• Origin links use main because these registry entries pin hashes, not repository revisions.

Benchmarks

No submitted benchmark reports yet.