Article
VKUE: No GPU? Runs Anyway โ a 34.7B Reasoner on a Laptop and on Bare CPU
FINAL-Bench
โข โข 17Jinki Jeong PRO
Anserwise
AI & ML interests
None yet
Recent Activity
upvoted an article 3 days ago
VKUE: No GPU? Runs Anyway โ a 34.7B Reasoner on a Laptop and on Bare CPU liked a Space 3 days ago
FINAL-Bench/VKUE liked a model 3 days ago
FINAL-Bench/Ourbox-35B-JGOS-GGUFOrganizations
None yet
upvoted an article 3 days ago
liked a
Space 3 days ago
liked a
model 3 days ago
reacted to SeaWolf-AI's post with โค๏ธ 3 days ago
Post
5288
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
upvoted an article 11 days ago
Article
Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier
FINAL-Bench
โข โข 15 reacted to SeaWolf-AI's post with ๐ฅ 11 days ago
Post
5156
๐ We ran genuine quantum key-recovery on 'real IBM quantum hardware' โ and pushed the frontier well past the largest hardware demos we're aware of (which sat at N=4).
Using Simon's algorithm on
โข EvenโMansour โ N=5 โ N=10
โข 3-round Feistel (DES-family) โ block 6 โ 8
Each verified against an 'independent control key', using error mitigation only (no QEC).
๐งญ Honest scope: this is not a quantum speedup (the effective difficulty tracks the classical birthday bound ~2^{n/2}), not a break of real AES/RSA, and not 16-round DES (ours is 3-round). The recovery method is reserved for a forthcoming paper; formal record status is pending peer review.
๐ Write-up: https://huggingface.co/blog/FINAL-Bench/quantum
๐น๏ธ Try it live in your browser: https://vidraft-quantumos.hf.space/crypto
๐ Leaderboard: FINAL-Bench/quantum-bench-leaderboard
#quantum #cryptography #quantumcomputing
Using Simon's algorithm on
ibm_kingston, we recovered the secret key of two symmetric-cipher structures:โข EvenโMansour โ N=5 โ N=10
โข 3-round Feistel (DES-family) โ block 6 โ 8
Each verified against an 'independent control key', using error mitigation only (no QEC).
๐งญ Honest scope: this is not a quantum speedup (the effective difficulty tracks the classical birthday bound ~2^{n/2}), not a break of real AES/RSA, and not 16-round DES (ours is 3-round). The recovery method is reserved for a forthcoming paper; formal record status is pending peer review.
๐ Write-up: https://huggingface.co/blog/FINAL-Bench/quantum
๐น๏ธ Try it live in your browser: https://vidraft-quantumos.hf.space/crypto
๐ Leaderboard: FINAL-Bench/quantum-bench-leaderboard
#quantum #cryptography #quantumcomputing
upvoted a collection 12 days ago
upvoted an article 12 days ago
Article
Adding a GPU Without Building One
FINAL-Bench
โข โข 17 reacted to SeaWolf-AI's post with ๐โค๏ธ 12 days ago
Post
3001
๐ Adding a GPU without building one
AI is usually framed as "how smart is the model / how many GPUs did you buy." The real bottleneck is elsewhere โ how efficiently you use the GPUs you already have.
Training happens once; inference runs the entire time users use your product. So a service's economics come down to cost per token. Inference acceleration uses software to pull several times more out of the same GPU โ the effect of plugging in one more "virtual GPU."
VIDRAFT's VKAE, measured (B200, same-harness, no quality loss):
Qwen3.5-35B-A3B (MoE): 25.7 โ 601 tok/s (23.4ร)
Darwin-36B-Opus (in-house MoE): 25.0 โ 280.8 (11.2ร)
10,000+ tok/s peak aggregate under concurrency
The key: it's reproducible โ model + serving shipped as one container.
docker pull vidraft/qwen35-vkae:601
Don't take our word for it โ run it yourself. The mechanism will be released as a paper.
๐ Leaderboard & demo ๐ VIDraft/vkae
Articles ๐ https://huggingface.co/blog/FINAL-Bench/vkae-leaderboard
AI is usually framed as "how smart is the model / how many GPUs did you buy." The real bottleneck is elsewhere โ how efficiently you use the GPUs you already have.
Training happens once; inference runs the entire time users use your product. So a service's economics come down to cost per token. Inference acceleration uses software to pull several times more out of the same GPU โ the effect of plugging in one more "virtual GPU."
VIDRAFT's VKAE, measured (B200, same-harness, no quality loss):
Qwen3.5-35B-A3B (MoE): 25.7 โ 601 tok/s (23.4ร)
Darwin-36B-Opus (in-house MoE): 25.0 โ 280.8 (11.2ร)
10,000+ tok/s peak aggregate under concurrency
The key: it's reproducible โ model + serving shipped as one container.
docker pull vidraft/qwen35-vkae:601
Don't take our word for it โ run it yourself. The mechanism will be released as a paper.
๐ Leaderboard & demo ๐ VIDraft/vkae
Articles ๐ https://huggingface.co/blog/FINAL-Bench/vkae-leaderboard
- 3 replies
liked 2
models 12 days ago
liked a
model 14 days ago
liked a
Space 14 days ago
upvoted an article 15 days ago
Article
Does Your LLM Know *When It's About to Be Wrong*?
ginigen-ai
โข โข 21 reacted to ginigen-ai's post with ๐ฅ 15 days ago
Post
10441
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 4
models 16 days ago