 ██ ██ ▓▓ ██   ModelRoom
 ██ ██ ██ ░░   Which local model packages fit your machine.
 ▓▓ ██ ░░ ░░   modelroom 0.1.0 · github.com/jm-vis/modelroom

 folder    not chosen yet          the first question asks where results live
 daemon    Ollama 0.34.2           reachable, 5 models, 4 of them local
 machine   workstation             not measured in this results folder yet

 Five steps: configuration, packages, context, measurement, results.
 Files are written as the run goes on. Esc leaves a list, Ctrl-C leaves at any point.

 ── Step 1 of 5  Configuration ──────────────────────────────────────────
 ? Where should results live?  this folder
 ? Which machines should the result cover?  this machine
   measured: one graphics card, 12 GB, 128 GB memory, confirmed by llmfit
 ✓ Configuration   <results>, 1 machine

 ── Step 2 of 5  Packages ───────────────────────────────────────────────
 ? What are you looking for?  qwen
 ? Show only repositories of a publisher or a listed packager?  Yes
   searched Hugging Face at the publisher Qwen and the five listed packagers
   4 repositories, 2 of them models you can pick from
 ? Which of these models should the result cover?  Qwen3.5-9B, DeepSeek-R1-0528-Qwen3-8B
 ✓ Packages        2 models, 24 packages from 3 repositories

 ── Step 3 of 5  Context ────────────────────────────────────────────────
 ? How much text should a model handle at once?  S  8k  6,000 words  a long conversation
 ✓ Context         S 8k

 ── Step 4 of 5  Measurement ────────────────────────────────────────────
 ? Measure the speed of the checked models that are already installed here?  Yes
 ? Which of these installed models should be measured?  hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M
   the load on this machine is read once, just before the runs -- load during a run is not measurable -- and the model behind the name must not change while the runs are made
   hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M: warm-up run
   hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M: run 1 of 3
   hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M: run 2 of 3
   hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M: run 3 of 3
   measured hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M: <speed>, context 8k
 ✓ Measurement     1 of 1 measured

 ── Step 5 of 5  Results ────────────────────────────────────────────────

 folder    <results>
 machine   workstation             12 GB graphics, 128 GB memory, measured today
 models    Qwen3.5-9B, DeepSeek-R1-0528-Qwen3-8B  24 packages from unsloth and Ollama
 context   S 8k                    6,000 words, a long conversation
 speed     1 measured              fastest DeepSeek-R1-0528-Qwen3-8B at <speed>
 result    docs\models.md          24 packages ranked, none too tight

 workstation · context S 8k
 #    Model                     Package                 Fit                   Speed         Memory
 ───────────────────────────────────────────────────────────────────────────────────────────────────
 1    DeepSeek-R1-0528-Qwen3-8  unsloth · Q4_K_M        good                  <speed>    6.8 GB
 2    Qwen3.5-9B                unsloth · UD-IQ2_XXS    good                  –             4.9 GB
 3    Qwen3.5-9B                unsloth · UD-IQ2_M      good                  –             5.4 GB
 4    Qwen3.5-9B                unsloth · UD-Q2_K_XL    good                  –             5.8 GB
 5    Qwen3.5-9B                unsloth · UD-IQ3_XXS    good                  –             5.7 GB
 6    Qwen3.5-9B                unsloth · Q3_K_S        good                  –             6.0 GB
 7    Qwen3.5-9B                unsloth · Q3_K_M        good                  –             6.4 GB
 8    Qwen3.5-9B                unsloth · UD-Q3_K_XL    good                  –             6.8 GB
 9    Qwen3.5-9B                unsloth · IQ4_XS        good                  –             6.9 GB
 10   Qwen3.5-9B                unsloth · IQ4_NL        good                  –             7.1 GB
 shown     10 of 24 packages
 memory    #1–10 fit into graphics memory, 11.0 GB free after the reserve
 basis     #2–10 computed from the package size, not its architecture
 speed     #1 measured <speed>

 install   #1  ollama pull hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M

 ✓ Results         docs\models.md
