OneJev 1.5 0.8B has 1.007 billion total parameters. The selected Q4_K_M GGUF file is 0.672 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
OmniJev
Total parameters
1,006,672,704
Exact file size
672,330,240 bytes
Quantization / precision
Q4_K_M
Weight repository
mradermacher/OneJev1.5-0.8B-GGUF
Original model repository
OmniJev/OneJev1.5-0.8B
Weight revision
57b376b8e75f3bc6cf861dbf8fc5c37a81213db9
Model revision
7106bc6ee2fb5d5e0163f6eb7b5c5e18a45ca975
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-12
Date evidence
OmniJev released the Apache-2.0 OneJev 1.5 0.8B source checkpoint on 12 October 2026. A complete third-party GGUF quantization set followed on 13 October; the selected 672,330,240-byte Q4_K_M file contains the language tensors, while multimodal use requires a separate vision projector and compatible runtime.
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.
Decision Index 0.3 · Public
42.71 / 100
Publisher-reported public-part score across 37 typed-decision benchmarks and 140,178 requests. This is not the full Decision Index composite, a general-chat score or an independent quantized-artifact benchmark.
Benchmark efficiency: 63.525 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: OmniJev reports a 42.71 score for the released source checkpoint on the public part of Decision Index 0.3: 37 typed-decision benchmarks and 140,178 requests, run and scored with the board's kit. The model receives text, images or video plus typed choice, yes/no or score questions and returns calibrated probabilities in one forward pass.
Publisher-run source-checkpoint result; not independent and not a measurement of the selected Q4_K_M GGUF. The publisher says the source checkpoint leads models up to 1.5B parameters on this public suite as of 12 October 2026, but this is a specialist decision score—not general chat, free-form generation, speed or arbitrary-agent performance. The source training mix includes training splits of public decision datasets. The third-party Q4 conversion was not independently executed here. Multimodal use also needs a separate 204,987,136-byte F16 or 115,923,712-byte Q8_0 projector, compatible Qwen3.5 vision support, runtime/KV memory and task-specific prompts; the selected language-file size alone does not establish hardware compatibility.
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 0.672 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 0.67 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 0.672 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.