0xSero reports running Inkling 2 Small on four RTX Pro 6000 cards at 190 tokens per second for decoding, with a 6-million-token KV cache pool using 4-bit EXL3 quantization, and calls it the best open-weight model (135 likes). Why it matters: S...
VQV Signal
OPEN SOURCE
WATCH
TECHNICAL
Inkling 2 Small hits 190 tokens per second on four workstation GPUs
0xSero reports running Inkling 2 Small on four RTX Pro 6000 cards at 190 tokens per second for decoding, with a 6-million-token KV cache pool using 4-bit EXL3 quantization, and calls it the best open-weight model (135 likes). Why it matters: S...
0xSero reports running Inkling 2 Small on four RTX Pro 6000 cards at 190 tokens per second for decoding, with a 6-million-token KV cache pool using 4-bit EXL3 quantization, and calls it the best open-weight model (135 likes). Why it matters: Strong open-weight models running fast on hardware a company can buy keep...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength 91%
Technical label WATCH
Public Interest 29
Category OPEN SOURCE
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 0
Practical Impact Score 20
Novelty Interest Score 70
Consequence Score 34
Curiosity Score 16
Shareability Score 45
Topics
VQV surfaced this signal because it is recent, relevant to LLM Inference, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.