OpenMobile-2 9B has 8.954 billion total parameters. The selected Q4_K_M GGUF file is 5.629 GB.
Data snapshot: . 5 published tests in this catalog.
Model file and details
Provider
OpenMobile-2
Total parameters
8,953,803,264
Exact file size
5,629,109,600 bytes
Quantization / precision
Q4_K_M
Weight repository
mradermacher/OpenMobile-2-9B-GGUF
Original model repository
OpenMobile-2/OpenMobile-2-9B
Weight revision
b785d866062fede13410acf29c84899dd08cc732
Model revision
407586f0eb3772bb0fa866b1a6e7faadd9c82035
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-09-28
Date evidence
The official source repository was created 28 September 2026 and its current benchmark card was revised 9 October; the complete static Q4_K_M conversion and vision projectors were published 10 October 2026.
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.
AndroidWorld Pass@1 · OpenMobile-2
74 / 100
Publisher-reported AndroidWorld Pass@1 for OpenMobile-2. Specialist mobile-agent benchmark; not a general intelligence, speed or local-quantization test.
Benchmark efficiency: 13.146 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: Publisher AndroidWorld Pass@1 table for the official source checkpoint. The card compares OpenMobile-2-9B with several mobile agents but does not disclose evaluation hardware, evaluator revision, task count or generation settings.
Publisher-run source-checkpoint result, not an independent evaluation and not a measurement of the selected Q4_K_M file. Local screenshot use also requires one separate vision projector. The 5,629,109,600-byte language-weight footprint excludes the projector, runtime, image tensors, KV cache and context memory and does not establish device speed or compatibility.
Publisher-reported MobileWorld GUI score for OpenMobile-2. Specialist mobile GUI-agent benchmark; not a general intelligence, speed or local-quantization test.
Benchmark efficiency: 6.839 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: Publisher MobileWorld GUI table for the official source checkpoint. The card does not disclose evaluation hardware, evaluator revision, task count or generation settings.
Publisher-run source-checkpoint result, not an independent evaluation and not a measurement of the selected Q4_K_M file. Cross-model values remain protocol-dependent.
Publisher-reported MobileGym success rate for OpenMobile-2. Specialist mobile-agent benchmark; not a general intelligence, speed or local-quantization test.
Benchmark efficiency: 6.804 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: Publisher MobileGym success-rate table for the official source checkpoint. The card does not disclose evaluation hardware, evaluator revision, task count or generation settings.
Publisher-run source-checkpoint result, not an independent evaluation and not a measurement of the selected Q4_K_M file.
Publisher-reported MobileGym++ Hybrid score for OpenMobile-2. Specialist mobile-agent benchmark; not a general intelligence, speed or local-quantization test.
Benchmark efficiency: 8.261 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: Publisher MobileGym++ Hybrid table for the official source checkpoint. The card does not disclose evaluation hardware, evaluator revision, task count or generation settings.
Publisher-run source-checkpoint result, not an independent evaluation and not a measurement of the selected Q4_K_M file.
Publisher-reported SPA-Bench L3 score for OpenMobile-2. Specialist app-native tool-use benchmark; not a general intelligence, speed or local-quantization test.
Benchmark efficiency: 8.687 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: Publisher SPA-Bench L3 table for the official source checkpoint. The benchmark concerns app-native tool use; the card does not disclose evaluation hardware, evaluator revision, task count or generation settings.
Publisher-run source-checkpoint result, not an independent evaluation and not a measurement of the selected Q4_K_M file.
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 5.629 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 5.63 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 5.629 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.