family member

Phi 4 REASONING-PLUS

3.3 tokens a second on Mac · Apple silicon · 10 CPUs · 16 GB RAM. No hosted API sells it, so this network is the place to run it.

3 builds of Phi 4 REASONING-PLUS, 3 signed runs on real machines: different packagers, precisions and engines, each a different file with its own numbers.

3.3tok/s, fastest machine

$60per M tokens · no API sells it

32Kcontext proved by recall

18.9 GBmemory, smallest build

2providers measured it

Use it in your own room Ask Evo in your gramx and it runs on a machine that proved it, at the metered $60 per million tokens. On your own machines it costs you nothing.Measure it on your machine A gram works through the catalog by itself and signs every result. 2 providers have measured Phi 4 REASONING-PLUS; every run is a point on the providers board.Compare every build Put it beside every other model in one table: speed, price, context and the API price, one row each.

best on ollama · 3 builds

trained 32K · proved 32K context, by unsloth Q4_K_M

24.5 tok/s peak, by unsloth Q4_K_M

What it fits on

The smallest build needs about 18.9 GB; 2 of 14 kinds of machine on the network can hold it. Bars: each kind's memory (its card's, else RAM) · ticks: every build, at the size it held plus a fifth for the prompt.

Linux, CPU only · 2 CPUs1 GB RAMnone
NVIDIA GeForce RTX 3050 Laptop GPU4 GB on the cardnone
NVIDIA GeForce GTX 16504 GB on the cardnone
AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAMnone
Windows, CPU only · 12 CPUs7 GB RAMnone
Apple silicon8 GB RAMnone
Apple M18 GB RAMnone
NVIDIA GeForce RTX 3080 Ti12 GB on the cardnone
Tesla T415 GB on the cardnone
Intel(R) UHD Graphics 73016 GB RAMnone
Intel(R) Iris(R) Xe Graphics16 GB RAMnone
Apple M416 GB RAMnone
2× Tesla T429 GB on the cardevery build
Linux, CPU only · 4 CPUs31 GB RAMevery build

How far back it remembers, machine by machine

Filled: the needle came back at that prompt size · outlined: asked and lost · blank: not asked · trained for 32K. 0 walks ended because the model forgot, 0 because the machine could not hold the prompt.

machine · build	4K	8K	16K	32K	why it stopped
Amit Khetan Tesla T4 · Q4_K_M by unsloth					32K recalled at every size asked
nitin singh Apple M4 · Q6_K by lmstudio-community					— an older probe: where it stopped was not recorded
nitin singh Apple M4 · Q4_K_M by lmstudio-community					— an older probe: where it stopped was not recorded

Measured by

The people whose machines signed these numbers

proved by at least one build: Structured output · Sustained output · Reasons about code · Synthesises sources · Follows instructions

Every build

Each its own file with its own page: the machines that ran it and their signatures.

build	engine	whose work	memory	context proved	best tok/s	machines
Q4_K_M by unslothhf.co/unsloth/Phi-4-reasoning-plus-GGUF:Q4_K_M	ollama	quantizer · unsloth	18.9 GB	32K	24.5	1
Q6_K by lmstudio-communityhf.co/lmstudio-community/Phi-4-reasoning-plus-GGUF:Q6_K	ollama	lmstudio-community	—	—	3.3	1
Q4_K_M by lmstudio-communityhf.co/lmstudio-community/Phi-4-reasoning-plus-GGUF:Q4_K_M	ollama	lmstudio-community	—	—	—	1