Curious 2B has 1.882 billion total parameters. The selected Q4_0 GGUF file is 1.215 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
Ebenezer Don
Total parameters
1,881,825,088
Exact file size
1,214,873,888 bytes
Quantization / precision
Q4_0
Weight repository
ebenezerdon/curious-2b
Original model repository
ebenezerdon/curious-2b
Weight revision
55485db6d09b96ccc0a9ce66aeb55706a51f9567
Model revision
55485db6d09b96ccc0a9ce66aeb55706a51f9567
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-12
Date evidence
The Apache-2.0 repository identifies curious-2b-261012 as the current 12 October 2026 release. On 13 October the publisher removed two model-card rows about identity and reading the phone, and clarified that unsupported-action and false-fact rates are lower-is-better; only README.md changed, while the selected 1,214,873,888-byte Q4_0 artifact remained byte-identical.
These scores were compiled from the linked sources. These published scores were not independently tested here. Different prompts, precision, thinking budgets and tools can change results.
CuriousLM · phone turns passed
86.1 / 100
Publisher-run held-out pass rate on 524 CuriousLM phone and calendar turns using the app's prompts and tool definitions. This is a project-specific release test, not a general agent benchmark.
Benchmark efficiency: 70.872 published score points per GB of selected weights. This ratio is not an inference-speed measure; check the test settings to see whether the score covers the selected quantization.
Test settings: The publisher compared Curious 2B 261012 with Qwen3.5 2B on 524 held-out phone and calendar turns under the same CuriousLM prompts and settings. Curious 2B passed 86.1% and the base model passed 62.6%.
Publisher-run, project-specific result; no independent reproduction or complete per-case protocol is supplied, and the card does not say that the selected Q4_0 artifact itself was benchmarked. The prompts and tool definitions are CuriousLM-specific. The same card reports lower general BFCL function-calling performance than the base model (54.8% versus 68.6%), so this result must not be generalized to arbitrary tools. The 13 October card revision removed identity and phone-reading rows that the catalog never used and clarified lower-is-better error metrics; the selected weights and this 524-turn result are unchanged. The 1,214,873,888-byte file excludes runtime, KV cache and context memory and does not establish device compatibility or speed. Apache-2.0 license.
Context and version evidence: The repository and file name identify the selected model. Revision hashes are shown above when recorded. Tested context length, full hardware configuration and run date are not consistently recorded in this snapshot. Only settings explicitly stated in each benchmark record are known.
The 1.215 GB figure covers model weights in this file. It excludes the context cache, runtime, operating system and any separate multimodal files. It is not a measured RAM requirement or a token-generation speed.
These complete configurations pass the initial weight-size check for the selected 1.21 GB file. Allow extra memory for context and software. Check the model’s runtime notes and your inference software before buying.
Listing evidence: 2026-09-25. Amazon.com base price visible in an owner-supplied screenshot reviewed 25 Sep 2026; capture time not supplied. Dated reference, not a live quote. Excludes card signup offers, coupons, tax and shipping.
Listing evidence: 2026-10-03. Apple US launch price announced 22 September 2026: USD 1,699. Dated manufacturer reference, not an Amazon offer; tax and shipping may differ.
Listing evidence: 2026-09-24. GMKtec, EVO-X2 / 64GB / 1TB, recorded 22 Sep 2026; exact ASIN capacity identified 24 Sep. This is a dated reference, not a current Amazon price; tax, shipping and bundle contents may differ.
Memory matches are estimates, not tested compatibility or speed. As an Amazon Associate I earn from qualifying purchases.
Confirm model architecture and quantization support in your runner. The selected weights use 1.215 GB; this excludes context cache, runtime buffers and other programs.
These are the first listed tiers that pass our reserve policy, not measured minimum requirements. System RAM and VRAM remain separate. Use the memory tool to change the reserve for your context and runner.