Steven Kramp 16 GB · RTX 4080
files too big
124.17 GB short
My measured card; usable free memory is not verified.
← All models and the lab diary
Steven Kramp / @SelfHostedSI · Local AI lab
MiniMax M2.7UD-Q4_K_M
File size only: 140.17 GB (display rounded to 0.01 GB); not run yet.
Download this model's data (JSON)Files, not parameter estimates
140.17 GB (display rounded to 0.01 GB)
140,169,905,504 bytes for this variant.
Source: Hugging Face file listing. Retrieved .
Hugging Face listings can change. These are dated file-size records; a revision hash was not retained. Download size does not prove that a runtime can load the model.
Fits on paper
Subtract this variant's recorded file size from each memory budget; the remainder is the upper bound for context and other overhead.
Decimal: 1 GB = 1,000,000,000 bytes; 1 TB = 1,000 GB. These are arithmetic comparison budgets, not verified usable hardware capacities. The answer can change with GB/GiB: 512 GiB = 549,755,813,888 bytes. The measured RTX 4080 has 16 GB VRAM; every other device name only labels a comparison budget.
24 GB · RTX 3090/4090
files too big
116.17 GB short
Comparison budget; not measured.
32 GB · RTX 5090
files too big
108.17 GB short
Comparison budget; not measured.
128 GB · DGX Spark
files too big
12.17 GB short
Comparison budget; I do not own one. Usable free memory is lower and not verified.
256 GB · Mac Studio M5 Ultra or 2× DGX Spark
files fit on paper
115.83 GB left
One Mac Studio M5 Ultra, or the sum of two DGX Sparks (two memories, not one pool). Not measured.
512 GB · Mac Studio M5 Ultra
files fit on paper
371.83 GB left
Planned; not delivered.
1 TB · 2× Mac Studio
files fit on paper
859.83 GB left
Across two planned machines; not one shared memory pool.
GB values are rounded to 0.01 GB for display; “left” is what remains for context, runtime and the operating system. Exact bytes are in this model's data (JSON).
Budget minus model files leaves an upper bound for context, runtime buffers and the operating system; no context length or runtime compatibility is promised. Exactly filling a budget leaves no room for context, so the answer is “no room for context on paper”; files larger than the budget are “files too big”.
Two Mac Studio machines, 512 GB each; not delivered. Two DGX Sparks are likewise two memories, not one pool. A model split across two machines needs a compatible runtime and must fit each machine's allocation. This table is arithmetic, not a cluster test.
Append-only run history · oldest first
Approved measurements
Output tokens/s, time to first token, measured context window, power and € per million tokens: not measured yet. No Mac measurements yet.
The JSON is an extract of approved measurement fields. Internal paths and operational notes are excluded. New runs append here; the model URL stays the same.