d3-edge 0.6B has 0.748 billion total parameters. The selected Q8_0 GGUF file is 0.806 GB.
Data snapshot: . 1 published test in this catalog.
Model file and details
Provider
vLLM Semantic Router
Total parameters
748,008,384
Exact file size
806,232,416 bytes
Quantization / precision
Q8_0
Weight repository
ggml-org/vllm-d3-edge-GGUF
Original model repository
vllm-sr/d3-edge
Weight revision
753af7a406f0025e46bb3af5b982b3e3590e522c
Model revision
20c745653400d191ecacd99c4eafc0c5900dc15e
Runtime notes
Confirm model architecture and quantization support in your runner.
Recorded release date
2026-10-10
Date evidence
The official Apache-2.0 source checkpoint was created on 10 October 2026; ggml-org published the pinned automatic Q8_0 llama.cpp conversion on 12 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.
Decision Index 0.3.1 · Composite
18 / 100
Publisher-reported Decision Index 0.3.1 composite across public, same-skill and new-domain typed-decision tasks. This is not a general chat, generation-speed or independent benchmark.
Benchmark efficiency: 22.326 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 evaluation with Decision Index 0.3.1. The card reports a composite 18.0, including 28.8 on the public suite, 23.9 on same-skill tests and 8.0 on new-domain tasks. The released source weights answered all 140,178 public requests, with choice, yes/no and score questions evaluated through the typed-decision interface.
Source-checkpoint result, not an independent test or a validation of the selected Q8_0 GGUF. d3-edge is a multimodal decision/classification model that returns option probabilities rather than chat text. The 806,232,416-byte language file excludes the separate 115,923,744-byte Q8_0 vision projector, runtime memory and context/KV memory. The source card's latency figures were measured on one AMD Instinct MI325X using the source runtime and must not be transferred to this GGUF or consumer hardware. The GGUF card requires llama.cpp System One support and points to pull request 30383; the source vLLM Semantic Router engine remained on its development channel at review time. 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 0.806 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 0.81 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 0.806 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.