 ██ ██ ▓▓ ██   ModelRoom
 ██ ██ ██ ░░   Which local model packages fit your machine.
 ▓▓ ██ ░░ ░░   modelroom 1.2.0 · 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
   another computer: pick its profile below, or import the file made there
 ? Which machines should the result cover?  this machine
 ? What kind of machine is this?  laptop
   graphics  NVIDIA RTX PRO 3000 Blackwell Generation Laptop GPU · 12.0 GB · nvidia-smi · usable (CUDA)
   graphics  Intel(R) Graphics · shared memory · windows · not counted: integrated graphics shares the system memory
   measured: laptop, 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
   catalog: shipped <day>
   searched Hugging Face at the publisher Qwen and the five listed packagers
   4 repositories, 2 of them models you can pick from
   Qwen3.5-27B (Qwen) is in the catalog; no GGUF from its publisher or a listed packager is known
   here
   Qwen3.5-122B-A10B (Qwen) is in the catalog; no GGUF from its publisher or a listed packager is
   known here
   Qwen3-Coder-30B-A3B-Instruct (Qwen) is in the catalog; no GGUF from its publisher or a listed
   packager is known here
 ? 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 many people work with it at the same time?  1 person (1 at once)
 ? 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 ────────────────────────────────────────────
   Ollama: 1 installed package of this run's models, one request each
 ? Measure the speed on this machine now?  Yes
 ? Which of these 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, protocol v2
 ✓ Measurement     1 of 1 measured

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

 folder    <results>
 machine   laptop-00000000         laptop, 12 GB graphics, 128 GB memory, measured today
 models    Qwen3.5-9B, DeepSeek-R1-0528-Qwen3-8B  24 packages from unsloth and Ollama
 context   8k (entered), KV cache f16 (assumed), 1 request (from 1 user)
 speed     1 measured              fastest DeepSeek-R1-0528-Qwen3-8B at <speed>, protocol v2
 result    docs\models.md          24 packages ranked, 0 no fit

 laptop-00000000 · context S 8k
 room      graphics 11.0 GB for models (12.0 GB card minus reserve)
           memory 111.7 GB for models (127.7 GB minus reserve)
           disk 41.2 GB free on C: (Ollama models)
 loaded    Ollama holds hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-… (5.7 GB, 5.7 GB of it on the card)
           graphics 10.2 GB free now
 #    Model                   Package                Fit          Speed         Memory    Download
 ───────────────────────────────────────────────────────────────────────────────────────────────────
 1    DeepSeek-R1-0528-Qwen3  unsloth · Q4_K_M       fits         <speed>    6.8 GB    4.7 GB
 2    Qwen3.5-9B              unsloth · Q8_0         tight        –             10.6 GB   8.9 GB
 shown     2 rows of 24 packages, one row per model
 memory    #1–2 fit into graphics memory, budget 11.0 GB (card minus reserve, from the profile)
 speed     #1 measured <speed>
 local     #1 already in Ollama on this computer
 key       Fit is memory only: the package's need against a pool · ample: up to 60 % of the pool
           fits: up to 85 % · tight: up to 98 % · no fit: more
           the pool is what the mode names, minus its reserve (per card) · gpu: one card
           gpu_split: all cards together · cpu_gpu, cpu (RAM): the system memory
           system memory keeps a quarter as reserve, 2 to 16 GB, unless modelroom.toml sets it
           one memory shared by system and card counts as gpu, a quarter kept, no upper limit
           off the card, and for a fit from size the highest class is fits
           best: the least compression of the same model that fits
           modelroom rates no model family against another
           one row per model, its least compression that fits
           a run with one model shows its first 10 packages, then the measured ones
           Speed is measured, see its column.

 install   #1  ollama pull hf.co/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_M
 Quality of these models for your task: https://artificialanalysis.ai

 ✓ Results         docs\models.md

 install   #1 is local already · say Yes in step 4 to measure it
