—per task?
price not verifiedprice
—output speed?
262Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open×3.9—$0 / —Context: 262K → 16K+2bOpenelephant-1 (9B)×3.4—$0 / —Context: 262K → 16K+2
BetterDecider v1.2Open×3.8—$0.02 / —Memory (4-bit): 0.3 GB → 15 GBABetterAutoTrust-JEV-27B v1.1Open×3.8——Memory (4-bit): 0.3 GB → 16 GB+1SBetterStartLux-Decision v1.1 27BOpen×3.8——Memory (4-bit): 0.3 GB → 16 GBModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open×3.9—$0 / —Context: 262K → 16K+2Decider v1.2Open×3.8—$0.02 / —Memory (4-bit): 0.3 GB → 15 GBAAutoTrust-JEV-27B v1.1Open×3.8——Memory (4-bit): 0.3 GB → 16 GB+1SStartLux-Decision v1.1 27BOpen×3.8——Memory (4-bit): 0.3 GB → 16 GBvD3 TurboOpen×3.8——Context: 262K → 33K+1ModelScoreCostPer taskWhat changes
belephant-1 (9B)Open×3.4—$0 / —Context: 262K → 16K+2Decider Flash v1.2Open×3.1—$0.01 / —Memory (4-bit): 0.3 GB → 2.7 GBvD3 FlashOpen×3.1——Memory (4-bit): 0.3 GB → 4.9 GBOOneJev1.6 9BOpen×3——Memory (4-bit): 0.3 GB → 5.5 GBFfrontier-infra Jebadiah 9B v2.1 (t1e)Open×2.9——Memory (4-bit): 0.3 GB → 5.7 GBModelScoreCostPer taskWhat changes
vD3 TurboOpen×3.8——Context: 262K → 33K+1vD3Open×3.8——Memory (4-bit): 0.3 GB → 15 GBvD3 FlashOpen×3.1——Memory (4-bit): 0.3 GB → 4.9 GBvD3 MiniOpen×2.8——Memory (4-bit): 0.3 GB → 2.7 GBvvLLM-SR Decision 2.0 Lux 9BOpen×2.6——Context: 262K → 16K+2vvLLM-SR Decision 2.0 Nox 4BOpen×2.3——Context: 262K → 16K+2vvLLM-SR d3-nano (2B)Open+94%——Memory (4-bit): 0.3 GB → 1.3 GBvvLLM-SR d3-lite (0.8B)Open+48%——Memory (4-bit): 0.3 GB → 0.5 GBAll vLLM Semantic Router models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
in Decision modelsFAQ
How much does vLLM-SR d3-edge (0.6B) cost?›
There is no per-unit API price: price not verified.
How good is vLLM-SR d3-edge (0.6B), and what is it best at?›
#82 of 99 in Decision models.
Is vLLM-SR d3-edge (0.6B) better than vLLM-SR Decision 2.0 Eos 0.8B?›
On Community Decision Index 0.4.1, vLLM-SR d3-edge (0.6B) scores 17.7 vs 18.4 — about the same.
What is the context window of vLLM-SR d3-edge (0.6B)?›
262K tokens.
When was vLLM-SR d3-edge (0.6B) released? Is there a newer version?›
Released 2026-10-10. It is the current version in its line.
Is vLLM-SR d3-edge (0.6B) open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run vLLM-SR d3-edge (0.6B) locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can vLLM-SR d3-edge (0.6B) read images?›
It accepts text and images, video as input.
What is vLLM-SR d3-edge (0.6B)?›
vLLM-SR d3-edge (0.6B) is an open-weights language model from vLLM Semantic Router, released Oct 2026.
What are the best alternatives to vLLM-SR d3-edge (0.6B)?›
mammoth-1 (27B) (better), elephant-1 (9B) (open weights).