family member
MiniCPM5 logo

MiniCPM5 1B

381 tokens a second on Windows · GeForce RTX 3080 Ti 12 GB · 16 CPUs · 16 GB RAM. No hosted API sells it, so this network is the place to run it.

1 build of MiniCPM5 1B, 4 signed runs on real machines: different packagers, precisions and engines, each a different file with its own numbers.

381tok/s, fastest machine
$0.67per M tokens · no API sells it
64Kcontext proved by recall
8.3 GBmemory, smallest build
4providers measured it
Run it on your gram Install a gram with one command. It works through the catalog on your own machine and signs every result. 4 providers have measured MiniCPM5 1B so far.Use it in your own room Ask Evo in your gramx and it runs on a machine that proved it, at the metered $0.67 per million tokens. On your own machines it costs you nothing.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 · 1 build

trained 128K · proved 64K context, by openbmb Q4_K_M

381.4 tok/s peak, by openbmb Q4_K_M

Speed against price, every machine

Up and left is faster and cheaper · the line joins machines no other beats on both · price on a log scale

$1USD per million tokenstok/sWindows · GeForce RTX 3080 Ti 12 GB · 16 CPUs · 16 GB RAM · 4-bit by openbmb · 381.36 tok/s · $0.6733/MLinux · L4 23 GB · 12 CPUs · 53 GB RAM · 4-bit by openbmb · 208.3 tok/s · $1.0381/MWindows · Intel 2 GB · 8 CPUs · 16 GB RAM · 4-bit by openbmb · 21.73 tok/s · $3.2909/MWindows · Intel(R) Iris(R) Xe Graphics 1 GB · 8 CPUs · 16 GB RAM · 4-bit by openbmb · 20.58 tok/s · $3.475/M

Same build, different machines

Q4_K_M by openbmb on 4 machines: the fastest decodes 18× as fast as the slowest. One dot per machine, tokens per second.

  1. NVIDIA GeForce RTX 3080 Ti×1381 tok/s
  2. NVIDIA L4×1208 tok/s
  3. Intel(R) Iris(R) Xe Graphics×125 tok/s
  4. Intel(R) UHD Graphics 730×122 tok/s

What it fits on

The smallest build needs about 8.3 GB; 10 of 18 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.

  1. Linux, CPU only · 2 CPUs1 GB RAMnone
  2. NVIDIA GeForce RTX 3050 Laptop GPU4 GB on the cardnone
  3. NVIDIA GeForce GTX 16504 GB on the cardnone
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAMnone
  5. Windows, CPU only · 12 CPUs7 GB RAMnone
  6. Apple silicon8 GB RAMnone
  7. Apple M18 GB RAMnone
  8. Mac, CPU only · 8 CPUs8 GB RAMnone
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the cardevery build
  10. Tesla T415 GB on the cardevery build
  11. Intel(R) UHD Graphics 73016 GB RAMevery build
  12. Intel(R) Iris(R) Xe Graphics16 GB RAMevery build
  13. Apple M416 GB RAMevery build
  14. Apple M116 GB RAMevery build
  15. NVIDIA L422 GB on the cardevery build
  16. 2× Tesla T429 GB on the cardevery build
  17. Linux, CPU only · 4 CPUs31 GB RAMevery build
  18. NVIDIA RTX PRO 6000 Blackwell Server Edition95 GB on the cardevery 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 128K. 1 walk ended because the model forgot, 2 because the machine could not hold the prompt.

machine · build4K8K16K32K64K128Kwhy it stopped
Gram ·dae679NVIDIA L4 · Q4_K_M by openbmb64K the model lost the needle at 128K
Gram ·9e3c79Intel(R) UHD Graphics 730 · Q4_K_M by openbmb8K this machine could not serve at 16K
Gram ·84bf54NVIDIA GeForce RTX 3080 Ti · Q4_K_M by openbmb4K recalled at every size asked
Gram ·2e5c02Intel(R) Iris(R) Xe Graphics · Q4_K_M by openbmb4K too slow to answer here

Carbon per million tokens

Lowest build on each machine · 2 of 4 read off a power sensor, the rest modelled from the parts · fewer grams is better

  1. Gram ·dae679183 g1.39 J/tok · sensor
  2. Gram ·84bf54352 g1.79 J/tok · sensor
  3. Gram ·2e5c02460 g2.34 J/tok · modelled
  4. Gram ·9e3c79589 g2.99 J/tok · modelled

Carbon is location-based: signed energy × the yearly average of the grid where the machine signed its place (world grid average (Singapore not in the table) · India grid average; Ember Global Electricity Review 2025 (2024 generation), location-based). Facility overhead is not included. A machine on its own solar is not credited until it can prove it.

Measured by

The people whose machines signed these numbers

proved by at least one build: Tool calling · Tool loop finished · Faithful to tool results · Structured output · Sustained output · Extended thinking · Writes code · 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.

buildenginewhose workmemorycontext provedbest tok/smachines
Q4_K_M by openbmbhf.co/openbmb/MiniCPM5-1B-GGUF:Q4_K_Mollamavendor · openbmb8.3 GB64K381.44
derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

MiniCPM5-1B-Agentic-Tooluse-v3-GGUFnot measuredMiniCPM5-1B-OptiQ-4bitnot measuredMiniCPM5-1B-hereticnot measured