shahondin1624
0 Followers · 0 Following
  • Germay
  • Joined on 2026-01-30
Repositories
7
 Projects Packages Public Activity Starred Repositories
shahondin1624 commented on issue llm-multiverse/llm-multiverse#6 2026-03-08 21:32:22 +01:00
Document hardware baseline and Ollama configuration

Baseline document created at docs/hardware-baseline.md and pushed to main.

Includes:

  • Hardware specs (GPU, RAM, CPU, OS, kernel)
  • Ollama configuration (install method, ROCm, service config) -…
shahondin1624 closed issue llm-multiverse/llm-multiverse#5 2026-03-08 21:31:24 +01:00
Pull and verify nomic-embed-text
shahondin1624 closed issue llm-multiverse/llm-multiverse#4 2026-03-08 21:31:23 +01:00
Pull and benchmark Qwen2.5 14B Instruct
shahondin1624 closed issue llm-multiverse/llm-multiverse#3 2026-03-08 21:31:23 +01:00
Pull and benchmark Qwen2.5-Coder 14B Instruct
shahondin1624 closed issue llm-multiverse/llm-multiverse#2 2026-03-08 21:31:22 +01:00
Pull and benchmark Qwen2.5 7B Instruct
shahondin1624 closed issue llm-multiverse/llm-multiverse#1 2026-03-08 21:31:21 +01:00
Install and verify Ollama on bare metal with RX 9070 XT
shahondin1624 commented on issue llm-multiverse/llm-multiverse#5 2026-03-08 21:31:15 +01:00
Pull and verify nomic-embed-text

Verification Results — nomic-embed-text

shahondin1624 commented on issue llm-multiverse/llm-multiverse#4 2026-03-08 21:31:11 +01:00
Pull and benchmark Qwen2.5 14B Instruct

Benchmark Results — qwen2.5:14b-instruct

shahondin1624 commented on issue llm-multiverse/llm-multiverse#3 2026-03-08 21:31:09 +01:00
Pull and benchmark Qwen2.5-Coder 14B Instruct

Benchmark Results — qwen2.5-coder:14b-instruct

shahondin1624 commented on issue llm-multiverse/llm-multiverse#2 2026-03-08 21:31:07 +01:00
Pull and benchmark Qwen2.5 7B Instruct

Benchmark Results — qwen2.5:7b-instruct

shahondin1624 commented on issue llm-multiverse/llm-multiverse#1 2026-03-08 21:31:04 +01:00
Install and verify Ollama on bare metal with RX 9070 XT

Results

  • GPU detected: AMD Radeon Graphics (gfx1201, RDNA4) — native support, no HSA_OVERRIDE_GFX_VERSION needed
  • VRAM: 15.9 GiB total, 12.6 GiB available at idle
  • Driver:…
shahondin1624 pushed to main at llm-multiverse/llm-multiverse 2026-03-08 20:57:56 +01:00
9865fa62bb chore: initial project structure with planning docs and CI commands
shahondin1624 opened issue llm-multiverse/llm-multiverse#99 2026-03-08 10:53:48 +01:00
Document multi-machine deployment guide
shahondin1624 opened issue llm-multiverse/llm-multiverse#98 2026-03-08 10:53:45 +01:00
Validate zero service code changes
shahondin1624 opened issue llm-multiverse/llm-multiverse#97 2026-03-08 10:53:40 +01:00
Convert docker-compose.yml to Swarm stack
shahondin1624 opened issue llm-multiverse/llm-multiverse#96 2026-03-08 10:53:36 +01:00
Define service placement constraints
shahondin1624 opened issue llm-multiverse/llm-multiverse#95 2026-03-08 10:53:33 +01:00
Initialize Docker Swarm and encrypted overlay
shahondin1624 opened issue llm-multiverse/llm-multiverse#94 2026-03-08 10:53:24 +01:00
Verify service DNS routing and connectivity
shahondin1624 opened issue llm-multiverse/llm-multiverse#93 2026-03-08 10:53:20 +01:00
Configure secrets service D-Bus socket mounting
shahondin1624 opened issue llm-multiverse/llm-multiverse#92 2026-03-08 10:53:16 +01:00
Configure Caddy v2 edge proxy