Your Ollama setup is probably lying to you.
Measure it in 3 minutes — free.

Most local LLM installs run on bad defaults and nobody notices: the context window silently truncates at ~4k (reads as "the model got dumb"), the model quietly spills to CPU at larger contexts, or a "smaller" KV cache setting actually makes things slower on your GPU. None of it shows up unless you measure on your own machine. This tool does exactly that — no guessing from spec sheets.

$ ollama-tune profile qwen3.5:9b

=== ollama-tune report: qwen3.5:9b ===

Hardware
  GPU     : AMD Radeon RX 6700 XT
  VRAM    : 12.0 GiB
  Backend : Vulkan          # what Ollama actually selected, read from its own log

Context sweep (placement + generation speed)
   num_ctx      on-GPU   gen tok/s    load s
      2048        100%        49.8       2.1
      8192        100%        49.1       2.3
     16384        100%        48.7       2.6
     32768        100%        47.9       3.1
     65536         81%         9.4       6.8   # the cliff
  prefill : ~273 tok/s over 3218 prompt tokens

Findings
  [warn] VRAM ceiling near 65536 tokens
  [warn] Default context silently truncates (model advertises 262144)
  [CRIT] Reasoning model — needs think control
  [i  ] Generation ~50 tok/s — memory-bandwidth-bound; kernel tweaks won't move this

Recommended config
  FROM qwen3.5:9b
  PARAMETER num_ctx 32768

Real output, real machine. The free report is the whole diagnosis — the paid tier is the one-click fix.

Download — the report is free, forever

Windows x64 (.zip) Linux x64 (.tar.gz)

macOS build coming. SHA-256 checksums. Single binary, no installer, no telemetry — it talks to your local Ollama and nothing else.

Free vs paid

FreeLicensed — $49
profile — full report + recommended config
list
apply — bake the tuned model + persist settings
profile --deep — empirical KV-cache A/B
serve — local web dashboard
$49 · one machine · yours forever · 12 months of updates

Licenses are per-seat (one computer), verified offline — no phone-home, no subscription lock-out. Every version released inside your 12-month window works forever; renewing (~$29/yr) is only for newer builds. 3 activation credits per seat cover reinstalls and hardware swaps. Air-gapped boxes activate from any browser on any device.

Buy a seat — email for early-access invoice

Card checkout is coming; early-access buyers get their key by email, usually within hours. 14-day refund, no questions.

What the licensed tier actually does

apply creates a <model>-tuned variant with the measured optimal context baked in and persists the right environment settings for your OS. --deep restarts Ollama with each KV-cache type and measures which one is actually faster on your card — we've measured q8_0 (the "obvious win") forcing a CPU spill on RDNA2/Vulkan; assumptions lose to measurement. serve gives you a local dashboard: click to profile, compare runs, apply the winner. It always restores stock settings, even if a run errors out.

Guides

Honest limitations

Generation speed is noisy if something else is using the GPU — profile on an idle card. The Linux/macOS hardware probes are newer than the Windows one. --deep restarts your local Ollama (and always restores it). The tool tunes the box it runs on — localhost only, by design.