Owner-operated, fully local inference

Private AI.
Protected remote access.

KevinBeLLM is an open-source AI workspace served from encrypted Ubuntu hardware. Its quality-tuned Qwen3.8-27B model runs fully on two consumer GPUs with xhigh reasoning, and authorized users can connect without opening a router port.

Open the private assistant See the request path

This public GitHub Pages site is informational only. Cloudflare Access verifies an authorized identity before KevinBeLLM presents its separate application login.

Useful independence

Local by design, connected on purpose.

The model and interface run on owned hardware; selected tools and authenticated remote access cross that boundary deliberately.

Local GPU inference

A checksum-pinned Q5_K_S quant stays split across the two GPUs with all model layers resident in VRAM.

Controlled live context

Xhigh reasoning is the default, while bounded tools can retrieve fresh web, news, weather, and model information when needed.

Two authentication gates

Cloudflare Access protects the tunnel route, and KevinBeLLM still requires its own login at the origin.

Public, auditable source

The application and deployment automation are published under the AGPL without publishing credentials or private data.

Measured on Machine A

More fidelity, tested on the same hardware.

The model, sampler, and memory settings are treated as one deployment profile and checked against a fixed local corpus before they become the default.

Local quality regression

15/16

Q5_K_S at the 45,056-token context passed 15 of 16 cases at seed 424242, including both long-thinking cases. The one miss is a string transform the model gets right about 40% of the time under any configuration.

Estimated AA-style neighborhood

≈47

A best-effort estimate for browser Think mode with a plausible 44–50 range—not an independently measured benchmark score. Fast mode sits near the hosted non-reasoning 35.

Production reasoning profile

xhigh

Official Qwen thinking sampling, preserved reasoning, 44K context, and up to 24,576 output tokens in the browser with a forced-answer reasoning budget.

The 16-case result is a single-seed deployment regression signal, not a general intelligence test. The ≈47 estimate adjusts the hosted model's reported xhigh result of 52 for this machine's quantization, 44K context, and 20,480-token thinking budget; only a complete standardized run could establish an official score. See the hosted-mode results ↗

Owned compute

One host. Two pooled GPUs.

Both cards live in Machine A and share one resident model without a network hop in the inference path.

Primary GPU

GeForce RTX 3060

VRAM: 12 GiB GDDR6
Link: PCIe 2.0 x16
Role: App, and the lower layers of the 27B model

Secondary GPU

GeForce RTX 3070

VRAM: 8 GiB GDDR6
Link: PCIe 2.0 x1 riser
Role: Holds the upper layers of the same model

Quality bought with careful memory tuning. Pooling both cards keeps the larger Q5_K_S quant entirely in VRAM with a 45,056-token context, q4_0 KV cache, and a measured 67/33 layer split that moves one layer's feed-forward weights to the 3070.

Encrypted cold boots require a person.

After shutdown or power loss, the machine must be physically powered on and have its LUKS passphrase entered. No remote feature bypasses that prompt.

Remote request path

No public origin port required.

Remote requests pass through two login boundaries before the local application can reach the model.

Your browserHTTPS request
Cloudflare AccessIdentity policy
Named TunnelOutbound connector
KevinBeLLM loginMachine A origin
Local llama.cppRTX 3060 + 3070 · Qwen3.8-27B Q5_K_S

GitHub Pages is not part of this request path. The public page contains no login form, origin address, tunnel credential, model endpoint, uptime badge, or live system status.

Clear boundaries

Local does not mean invisible.

Model inference can remain on owned hardware, but an intentional web search sends the search query to configured providers and downloads selected pages. Remote access also passes through Cloudflare before reaching Machine A.

Treat model output as a starting point. Verify important medical, legal, financial, security, and operational decisions against primary sources.

Authorized users

Enter the protected workspace.

Continue to Cloudflare Access. KevinBeLLM will request its own login after the identity policy succeeds.

Continue to authenticated access