FINAL-Bench/Ourbox-35B-JGOS-GGUF
Text Generation โข 35B โข Updated โข 861 โข 26
AIQ
aiqcamp
AI & ML interests
None yet
Recent Activity
liked a model 4 days ago
FINAL-Bench/Ourbox-35B-JGOS-GGUF liked a Space 4 days ago
FINAL-Bench/VKUE reacted to SeaWolf-AI's post with โค๏ธ 4 days 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 4 days ago
liked a
Space 4 days ago
reacted to SeaWolf-AI's post with โค๏ธโ 4 days ago
Post
5303
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.
- 6 replies
liked 2
models 13 days ago
liked a
model 14 days ago
liked a
Space 15 days ago
reacted to ginigen-ai's post with ๐ฅ 15 days ago
Post
5198
๐ณ The RoboCasa Kitchen Leaderboard
What does it take for a robot to handle kitchen chores the way a person does? It has to see (Vision), understand instructions (Language), and actually act (Action) โ and VLA (Vision-Language-Action) models are emerging as the answer. They're the bridge between large multimodal models and real-world embodied control.
RoboCasa Kitchen is a leading robot-learning benchmark in which a single-arm robot (Franka Panda) performs 24 atomic manipulation tasks โ picking up cups and bowls, opening drawers and doors, turning faucets, pressing buttons, and more โ inside a photorealistic simulated kitchen. Because the layout and object placement are randomized every episode, it tests genuine generalization rather than memorized motions. The score (success rate, SR) is the average fraction of the 24 tasks completed as instructed, measured over multiple seeds so results aren't down to luck.
The catch: this benchmark has no official leaderboard, and protocols (number of demonstrations, evaluation setup) differ from paper to paper, leaving scores scattered. Lining the numbers up naively quickly turns into an apples-to-oranges comparison.
This leaderboard fixes that by collecting published scores with their sources and comparing only what is genuinely comparable. It's split into three tables:
๐ Kitchen 24-task (matched) โ head-to-head under identical conditions (per the RLDX-1 Technical Report). This is the core ranking you can actually trust.
โ Other protocols โ self-reported under different setups (e.g. fewer demos). Not directly comparable, so kept separate.
๐ค GR1-Tabletop โ a different, humanoid-based variant suite, separated to avoid confusion.
Any researcher can submit their own model's score directly, and submissions are reviewed before they appear on the board. Every number links to its source paper, so you can verify it yourself.
๐ ginigen-ai/robocasa-kitchen-leaderboard
What does it take for a robot to handle kitchen chores the way a person does? It has to see (Vision), understand instructions (Language), and actually act (Action) โ and VLA (Vision-Language-Action) models are emerging as the answer. They're the bridge between large multimodal models and real-world embodied control.
RoboCasa Kitchen is a leading robot-learning benchmark in which a single-arm robot (Franka Panda) performs 24 atomic manipulation tasks โ picking up cups and bowls, opening drawers and doors, turning faucets, pressing buttons, and more โ inside a photorealistic simulated kitchen. Because the layout and object placement are randomized every episode, it tests genuine generalization rather than memorized motions. The score (success rate, SR) is the average fraction of the 24 tasks completed as instructed, measured over multiple seeds so results aren't down to luck.
The catch: this benchmark has no official leaderboard, and protocols (number of demonstrations, evaluation setup) differ from paper to paper, leaving scores scattered. Lining the numbers up naively quickly turns into an apples-to-oranges comparison.
This leaderboard fixes that by collecting published scores with their sources and comparing only what is genuinely comparable. It's split into three tables:
๐ Kitchen 24-task (matched) โ head-to-head under identical conditions (per the RLDX-1 Technical Report). This is the core ranking you can actually trust.
โ Other protocols โ self-reported under different setups (e.g. fewer demos). Not directly comparable, so kept separate.
๐ค GR1-Tabletop โ a different, humanoid-based variant suite, separated to avoid confusion.
Any researcher can submit their own model's score directly, and submissions are reviewed before they appear on the board. Every number links to its source paper, so you can verify it yourself.
๐ ginigen-ai/robocasa-kitchen-leaderboard
reacted to ginigen-ai's post with ๐ 15 days ago
Post
10442
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 16 days ago
FINAL-Bench/metacog-adapter-Ornith-1.0-9B
Updated โข 45 โข 23
FINAL-Bench/metacog-adapter-Darwin-28B-Opus
Updated โข 45 โข 23
FINAL-Bench/metacog-adapter-Darwin-9B-NEG
Updated โข 45 โข 21
FINAL-Bench/metacog-adapter-Qwen-AgentWorld-35B-A3B
Updated โข 56 โข 21
FINAL-Bench/metacog-adapter-Qwen3.5-27B
Updated โข 51 โข 20
FINAL-Bench/metacog-adapter-Qwen3.5-35B-A3B
Updated โข 62 โข 20
FINAL-Bench/metacog-adapter-Qwen3.5-9B
Updated โข 54 โข 20
FINAL-Bench/metacog-adapter-gemma-4-12B-it
Updated โข 52 โข 20
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