FINAL-Bench/Ourbox-35B-JGOS-GGUF
Text Generation โข 35B โข Updated โข 1 โข 23
master PRO
fantos
AI & ML interests
None yet
Recent Activity
liked a model about 9 hours ago
FINAL-Bench/Ourbox-35B-JGOS-GGUF liked a Space about 9 hours ago
FINAL-Bench/VKUE reacted to SeaWolf-AI's post with ๐ฅ about 9 hours ago
๐ต VKUE โ No GPU? Runs anyway.
"Frontier models need a datacenter GPU" rests on a hidden assumption: that the model reads ALL its parameters every token. Decode is memory-bandwidth bound โ sweep 34B params/token and an 8 GB card dies at 1โ2 tok/s.
So we ran ONE 34.7B reasoning model โ Ourbox-35B-JGOS, a sparse Mixture-of-Experts โ as the identical weights across the whole hardware spectrum. All measured:
โข B200: 18,057 tok/s (aggregate)
โข 1ร A10G: 126 tok/s
โข 8 GB laptop (RTX 5060): 20 tok/s
โข GPU-less CPU: 17 tok/s
Why it works: Ourbox holds 34.7B params but only ~3B are active per token (256 experts, top-8). Since decode is bandwidth-bound, a dense 34B moves ~16.7 GB/token while Ourbox moves ~1.45 GB โ ~11ร less traffic. Put the experts in system RAM, keep attention/router/shared on the GPU, and a 34.7B reasoner runs on an 8 GB laptop โ or no GPU at all.
Sparsity alone, proven (same laptop, same quant, ~same footprint): Ourbox-35B (A3B) 20.01 tok/s vs Qwen2.5-32B (dense) 5.36 โ 3.7ร from sparsity alone, ~2ร the best dense-32B on any 8 GB machine. Not a toy: GPQA Diamond 86.4% (maj@8).
Try it live (same prompt, GPU vs GPU-less CPU, live tok/s). Honest scope: one machine's measurements; the CPU path proves it RUNS without a GPU, not that it beats one.
๐ Article: https://huggingface.co/blog/FINAL-Bench/vkue
๐ต GPU vs CPU demo: https://final-bench-ourbox-35b-vkue-demo.hf.space/
๐ต CPU-only demo: https://final-bench-ourbox-35b-vkue-cpu.hf.space
๐ VKUE leaderboard: https://huggingface.co/spaces/FINAL-Bench/VKUE
๐ค Model: https://huggingface.co/FINAL-Bench/Ourbox-35B-JGOS-GGUF
โก VKAE (speed): https://huggingface.co/spaces/VIDraft/vkae
VKUE is the "runs anywhere" side of our serving line; VKAE the "fast on datacenter GPUs" side. VKAE is fast; VKUE is everywhere.Organizations
liked a
model about 9 hours ago
liked a
Space about 9 hours ago
reacted to SeaWolf-AI's post with ๐ฅ about 9 hours ago
Post
538
๐ต VKUE โ No GPU? Runs anyway.
"Frontier models need a datacenter GPU" rests on a hidden assumption: that the model reads ALL its parameters every token. Decode is memory-bandwidth bound โ sweep 34B params/token and an 8 GB card dies at 1โ2 tok/s.
So we ran ONE 34.7B reasoning model โ Ourbox-35B-JGOS, a sparse Mixture-of-Experts โ as the identical weights across the whole hardware spectrum. All measured:
โข B200: 18,057 tok/s (aggregate)
โข 1ร A10G: 126 tok/s
โข 8 GB laptop (RTX 5060): 20 tok/s
โข GPU-less CPU: 17 tok/s
Why it works: Ourbox holds 34.7B params but only ~3B are active per token (256 experts, top-8). Since decode is bandwidth-bound, a dense 34B moves ~16.7 GB/token while Ourbox moves ~1.45 GB โ ~11ร less traffic. Put the experts in system RAM, keep attention/router/shared on the GPU, and a 34.7B reasoner runs on an 8 GB laptop โ or no GPU at all.
Sparsity alone, proven (same laptop, same quant, ~same footprint): Ourbox-35B (A3B) 20.01 tok/s vs Qwen2.5-32B (dense) 5.36 โ 3.7ร from sparsity alone, ~2ร the best dense-32B on any 8 GB machine. Not a toy: GPQA Diamond 86.4% (maj@8).
Try it live (same prompt, GPU vs GPU-less CPU, live tok/s). Honest scope: one machine's measurements; the CPU path proves it RUNS without a GPU, not that it beats one.
๐ Article: https://huggingface.co/blog/FINAL-Bench/vkue
๐ต GPU vs CPU demo: https://final-bench-ourbox-35b-vkue-demo.hf.space/
๐ต CPU-only demo: https://final-bench-ourbox-35b-vkue-cpu.hf.space
๐ VKUE leaderboard: FINAL-Bench/VKUE
๐ค Model: FINAL-Bench/Ourbox-35B-JGOS-GGUF
โก VKAE (speed): VIDraft/vkae
VKUE is the "runs anywhere" side of our serving line; VKAE the "fast on datacenter GPUs" side. VKAE is fast; VKUE is everywhere.
"Frontier models need a datacenter GPU" rests on a hidden assumption: that the model reads ALL its parameters every token. Decode is memory-bandwidth bound โ sweep 34B params/token and an 8 GB card dies at 1โ2 tok/s.
So we ran ONE 34.7B reasoning model โ Ourbox-35B-JGOS, a sparse Mixture-of-Experts โ as the identical weights across the whole hardware spectrum. All measured:
โข B200: 18,057 tok/s (aggregate)
โข 1ร A10G: 126 tok/s
โข 8 GB laptop (RTX 5060): 20 tok/s
โข GPU-less CPU: 17 tok/s
Why it works: Ourbox holds 34.7B params but only ~3B are active per token (256 experts, top-8). Since decode is bandwidth-bound, a dense 34B moves ~16.7 GB/token while Ourbox moves ~1.45 GB โ ~11ร less traffic. Put the experts in system RAM, keep attention/router/shared on the GPU, and a 34.7B reasoner runs on an 8 GB laptop โ or no GPU at all.
Sparsity alone, proven (same laptop, same quant, ~same footprint): Ourbox-35B (A3B) 20.01 tok/s vs Qwen2.5-32B (dense) 5.36 โ 3.7ร from sparsity alone, ~2ร the best dense-32B on any 8 GB machine. Not a toy: GPQA Diamond 86.4% (maj@8).
Try it live (same prompt, GPU vs GPU-less CPU, live tok/s). Honest scope: one machine's measurements; the CPU path proves it RUNS without a GPU, not that it beats one.
๐ Article: https://huggingface.co/blog/FINAL-Bench/vkue
๐ต GPU vs CPU demo: https://final-bench-ourbox-35b-vkue-demo.hf.space/
๐ต CPU-only demo: https://final-bench-ourbox-35b-vkue-cpu.hf.space
๐ VKUE leaderboard: FINAL-Bench/VKUE
๐ค Model: FINAL-Bench/Ourbox-35B-JGOS-GGUF
โก VKAE (speed): VIDraft/vkae
VKUE is the "runs anywhere" side of our serving line; VKAE the "fast on datacenter GPUs" side. VKAE is fast; VKUE is everywhere.
liked 2
models 9 days ago
liked a
model 11 days ago
liked a
Space 11 days ago
reacted to ginigen-ai's post with ๐โค๏ธ๐ฅ 12 days ago
Post
10429
๐ง Does your LLM know when it's about to be wrong?
Most leaderboards measure accuracy. We measure metacognition โ whether a model catches its own errors. Benchmark + leaderboard + adapters, all open. ๐
The surprise: even a K-AI #1 model (JGOS-31B-Citizen) is the strongest on multiple-choice traps (trap_rate 0.005 โ ~2 misses in 400) yet blind to its own free-form mistakes (self-confidence AUROC = 0.5, pure random). A tiny base-frozen adapter recovers that signal.
Two independent axes (never compared across a row): โ trap_rate โ does it fall for tempting trap options? (lower = stronger) โก adapter gain ฮ โ how much a lightweight adapter catches errors the model itself misses. (higher = more adapter value)
What's open: ๐ 300+100 trap problems (each with a hidden trap + TICOS type) ๐ 24-model leaderboard ๐งฉ 11 per-model adapters โ adapters, NOT fine-tunes (base stays frozen; the adapter just reads the hidden state โ P(wrong))
Submit any HF model โ auto-scored daily at 09:00 KST and added to the board.
๐ Leaderboard โ ginigen-ai/Metacognition-Leaderboard-Space
๐ Benchmark โ ginigen-ai/Metacognition-Bench
๐งฉ Adapters โ FINAL-Bench/metacognition-adapters-6a42c032e6beb803dd032961
๐ Article โ https://huggingface.co/blog/ginigen-ai/metacognition
Benchmark by ginigen-ai ยท Adapters by FINAL-Bench (Darwin/Chimera platform + AETHER metacognition tech).
Most leaderboards measure accuracy. We measure metacognition โ whether a model catches its own errors. Benchmark + leaderboard + adapters, all open. ๐
The surprise: even a K-AI #1 model (JGOS-31B-Citizen) is the strongest on multiple-choice traps (trap_rate 0.005 โ ~2 misses in 400) yet blind to its own free-form mistakes (self-confidence AUROC = 0.5, pure random). A tiny base-frozen adapter recovers that signal.
Two independent axes (never compared across a row): โ trap_rate โ does it fall for tempting trap options? (lower = stronger) โก adapter gain ฮ โ how much a lightweight adapter catches errors the model itself misses. (higher = more adapter value)
What's open: ๐ 300+100 trap problems (each with a hidden trap + TICOS type) ๐ 24-model leaderboard ๐งฉ 11 per-model adapters โ adapters, NOT fine-tunes (base stays frozen; the adapter just reads the hidden state โ P(wrong))
Submit any HF model โ auto-scored daily at 09:00 KST and added to the board.
๐ Leaderboard โ ginigen-ai/Metacognition-Leaderboard-Space
๐ Benchmark โ ginigen-ai/Metacognition-Bench
๐งฉ Adapters โ FINAL-Bench/metacognition-adapters-6a42c032e6beb803dd032961
๐ Article โ https://huggingface.co/blog/ginigen-ai/metacognition
Benchmark by ginigen-ai ยท Adapters by FINAL-Bench (Darwin/Chimera platform + AETHER metacognition tech).
- 11 replies
liked 10
models 13 days ago
FINAL-Bench/metacog-adapter-Darwin-28B-Opus
Updated โข 45 โข 23
FINAL-Bench/metacog-adapter-FastContext-1.0-4B-SFT
Updated โข 49 โข 21
FINAL-Bench/metacog-adapter-gemma-4-26B-A4B-it
Updated โข 63 โข 20
FINAL-Bench/metacog-adapter-gemma-4-12B-it
Updated โข 52 โข 20
FINAL-Bench/metacog-adapter-Qwen3.5-9B
Updated โข 54 โข 20
FINAL-Bench/metacog-adapter-Qwen3.5-35B-A3B
Updated โข 62 โข 20
FINAL-Bench/metacog-adapter-Qwen3.5-27B
Updated โข 51 โข 20
FINAL-Bench/metacog-adapter-Qwen-AgentWorld-35B-A3B
Updated โข 56 โข 21
FINAL-Bench/metacog-adapter-Darwin-9B-NEG
Updated โข 45 โข 21
FINAL-Bench/metacog-adapter-Ornith-1.0-9B
Updated โข 45 โข 23