Issues

• plan: --target-tps marks the GPU path infeasible even when its own estimated_tps is above the target

  bug
  AlexsJones/llmfit#1253 · Filter by author jan-stegeman opened on Nov 11, 2026
  1

• Weekly refresh fails: two HF configs push context_length past u32

  bug
  AlexsJones/llmfit#1246 · Filter by author Akciali opened on Nov 9, 2026
  1

• Windows / AMD Radeon 780M: 4 GB detected instead of 16 GB allocated

  bug
  AlexsJones/llmfit#1232 · Filter by author MPICOLLET opened on Nov 5, 2026
  1

• [Feature]: Cluster mode: calibrate multi-node memory and speed against measured runs

  Calibrationenhancement
  AlexsJones/llmfit#1227 · Filter by author michaeljabbour opened on Nov 3, 2026
  1

• [Feature]: Cluster mode: pipeline parallelism across nodes (TP within a node, PP across nodes)

  enhancement
  AlexsJones/llmfit#1226 · Filter by author michaeljabbour opened on Nov 3, 2026
  1

• [Feature]: Add minimal Strata inference runtime support

  enhancementIntegration
  AlexsJones/llmfit#1182 · Filter by author MarsLuay opened on Oct 22, 2026
  2

• [Docs]: winget install

  documentation
  AlexsJones/llmfit#1168 · Filter by author SamHasler opened on Oct 20, 2026
  1

• [Feature]: Optional MCP example for researching hardware-fit models

  Feature Request
  AlexsJones/llmfit#1133 · Filter by author georgeatparallel opened on Oct 11, 2026
  1

• [Feature]: Improving model selection with benchmarked database

  enhancement
  AlexsJones/llmfit#1116 · Filter by author MarsLuay opened on Oct 6, 2026
  1

• [Feature]: Add llama.cpp RCP-aware distributed hardware fitting

  enhancement
  AlexsJones/llmfit#1106 · Filter by author MarsLuay opened on Oct 3, 2026
  1

• [Calibration]: Detect PCIe link speed/topology for accurate calibration and throughput estimates

  enhancement
  AlexsJones/llmfit#1090 · Filter by author MarsLuay opened on Sep 27, 2026
  4

• Fit estimates don't account for Unsloth Studio's beyond-VRAM offload

  Data CollectionenhancementHardware Compatibilityhelp wanted
  AlexsJones/llmfit#1036 · Filter by author kushalBanda opened on Sep 14, 2026
  4

• [Feature]: mutiple GPU = total VRAM

  enhancement
  AlexsJones/llmfit#1018 · Filter by author Popov007 opened on Sep 10, 2026
  2

• [Feature]: Add a guided CLI wizard for goal-driven model recommendations

  enhancement
  AlexsJones/llmfit#1015 · Filter by author HassanAbdullahHere opened on Sep 9, 2026
  3

• Feature request: llmfit self-update mechanism

  enhancement
  AlexsJones/llmfit#930 · Filter by author take566 opened on Aug 21, 2026
  2

• [Feature]: Support LM Studio in Inference Bench (Quality Benchmarks / Routing)

  enhancement
  AlexsJones/llmfit#928 · Filter by author nidhi-singh02 opened on Aug 21, 2026
  4

• [Feature]: Recommendations for Tool-Using Coding Agents

  enhancement
  AlexsJones/llmfit#914 · Filter by author martosc opened on Aug 19, 2026
  7

• [Feature]: Inference bench tui improvements

  enhancement
  AlexsJones/llmfit#909 · Filter by author darukutsu opened on Aug 18, 2026
  1

• [Feature]: Ability to share selected benchmarks

  enhancement
  AlexsJones/llmfit#867 · Filter by author datawookie opened on Aug 12, 2026
  2

• Canonical vocabulary for fit_level/run_mode/runtime: does the CLI adopt the machine codes?

  enhancement
  AlexsJones/llmfit#803 · Filter by author aramz33 opened on Jul 27, 2026
  2

• Detect multiple GPUs

  enhancement
  AlexsJones/llmfit#638 · Filter by author agileramblings opened on Jun 17, 2026
  12

• MacBook Neo shows no models under "Good" or "Runnable" due to conservative KV cache filtering

  bug
  AlexsJones/llmfit#635 · Filter by author goney3 opened on Jun 15, 2026
  7

• Server mode: capacity planning / density calculation for 27B models

  enhancementFeasibility
  AlexsJones/llmfit#542 · Filter by author three-foxes-in-a-trenchcoat opened on May 11, 2026
  1

• Request to add support for NPU and Hybrid models

  enhancementFeature RequestHardware Compatibility
  AlexsJones/llmfit#301 · Filter by author GautamMKGarg opened on Mar 31, 2026
  12

• Should big pickle from opencode zen be added as a model?

  AlexsJones/llmfit#273 · Filter by author chicks-net opened on Mar 21, 2026
  1