VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU
• 14
AI & ML interests
Contact: arxivgpt@gmail.com
Recent Activity
View all activity
Papers
View all Papers Articles
SeaWolf-AI
posted an update about 16 hours ago
Post
1060
🔵 VKUE — 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 — sweep 34B params/token and an 8 GB card dies at 1–2 tok/s.
So we ran ONE 34.7B reasoning model — Ourbox-35B-JGOS, a sparse Mixture-of-Experts — as the identical weights across the whole hardware spectrum. All measured:
• B200: 18,057 tok/s (aggregate)
• 1× A10G: 126 tok/s
• 8 GB laptop (RTX 5060): 20 tok/s
• 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 — ~11× 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 — 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 → 3.7× from sparsity alone, ~2× 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.
📝 Article: https://huggingface.co/blog/FINAL-Bench/vkue
🔵 GPU vs CPU demo: https://final-bench-ourbox-35b-vkue-demo.hf.space/
🔵 CPU-only demo: https://final-bench-ourbox-35b-vkue-cpu.hf.space
📊 VKUE leaderboard: FINAL-Bench/VKUE
🤗 Model: FINAL-Bench/Ourbox-35B-JGOS-GGUF
⚡ 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 — sweep 34B params/token and an 8 GB card dies at 1–2 tok/s.
So we ran ONE 34.7B reasoning model — Ourbox-35B-JGOS, a sparse Mixture-of-Experts — as the identical weights across the whole hardware spectrum. All measured:
• B200: 18,057 tok/s (aggregate)
• 1× A10G: 126 tok/s
• 8 GB laptop (RTX 5060): 20 tok/s
• 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 — ~11× 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 — 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 → 3.7× from sparsity alone, ~2× 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.
📝 Article: https://huggingface.co/blog/FINAL-Bench/vkue
🔵 GPU vs CPU demo: https://final-bench-ourbox-35b-vkue-demo.hf.space/
🔵 CPU-only demo: https://final-bench-ourbox-35b-vkue-cpu.hf.space
📊 VKUE leaderboard: FINAL-Bench/VKUE
🤗 Model: FINAL-Bench/Ourbox-35B-JGOS-GGUF
⚡ 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.
SeaWolf-AI
published an article about 16 hours ago
Article
VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU
FINAL-Bench
• • 14 SeaWolf-AI
updated a
model about 20 hours ago
SeaWolf-AI
published a
model about 20 hours ago
SeaWolf-AI
updated a
Space about 22 hours ago
SeaWolf-AI
published a
Space about 22 hours ago
SeaWolf-AI
updated a
collection 1 day ago
SeaWolf-AI
updated a
Space 2 days ago
SeaWolf-AI
updated a
Space 5 days ago
SeaWolf-AI
published a
Space 5 days ago
fp8 of DARWIN 398b BF16?
🔥 1
2
#1 opened 8 days ago
by 
hfmefi69
SeaWolf-AI
posted an update 8 days ago
Post
5139
🔓 We ran genuine quantum key-recovery on 'real IBM quantum hardware' — and pushed the frontier well past the largest hardware demos we're aware of (which sat at N=4).
Using Simon's algorithm on
• Even–Mansour — N=5 → N=10
• 3-round Feistel (DES-family) — block 6 → 8
Each verified against an 'independent control key', using error mitigation only (no QEC).
🧭 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.
📄 Write-up: https://huggingface.co/blog/FINAL-Bench/quantum
🕹️ Try it live in your browser: https://vidraft-quantumos.hf.space/crypto
🏆 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:• Even–Mansour — N=5 → N=10
• 3-round Feistel (DES-family) — block 6 → 8
Each verified against an 'independent control key', using error mitigation only (no QEC).
🧭 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.
📄 Write-up: https://huggingface.co/blog/FINAL-Bench/quantum
🕹️ Try it live in your browser: https://vidraft-quantumos.hf.space/crypto
🏆 Leaderboard: FINAL-Bench/quantum-bench-leaderboard
#quantum #cryptography #quantumcomputing
SeaWolf-AI
published an article 8 days ago
Article
Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier
FINAL-Bench
• • 15 SeaWolf-AI
updated 2
models 9 days ago
SeaWolf-AI
updated 2
collections 9 days ago
SeaWolf-AI
posted an update 10 days ago
Post
2996
🚀 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 — 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 — 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 → 601 tok/s (23.4×)
Darwin-36B-Opus (in-house MoE): 25.0 → 280.8 (11.2×)
10,000+ tok/s peak aggregate under concurrency
The key: it's reproducible — model + serving shipped as one container.
docker pull vidraft/qwen35-vkae:601
Don't take our word for it — run it yourself. The mechanism will be released as a paper.
🏆 Leaderboard & demo 👉 VIDraft/vkae
Articles 👉 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 — 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 — 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 → 601 tok/s (23.4×)
Darwin-36B-Opus (in-house MoE): 25.0 → 280.8 (11.2×)
10,000+ tok/s peak aggregate under concurrency
The key: it's reproducible — model + serving shipped as one container.
docker pull vidraft/qwen35-vkae:601
Don't take our word for it — run it yourself. The mechanism will be released as a paper.
🏆 Leaderboard & demo 👉 VIDraft/vkae
Articles 👉 https://huggingface.co/blog/FINAL-Bench/vkae-leaderboard
- 3 replies