family member

e2b~bartowski

7 builds of e2b~bartowski, 7 signed runs on real machines: different packagers, precisions and engines, each a different file with its own numbers.

87tok/s, fastest machine
128Kcontext proved by recall
2.4 GBmemory, smallest build
1provider 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. 1 provider has measured e2b~bartowski so far.Use it in your own room Ask Evo in your gramx and it runs on a machine that proved it. 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 · 7 builds

trained 128K · proved 128K context, by bartowski Q4_0

87.3 tok/s peak, by bartowski Q4_0

What it fits on

The smallest build needs about 2.4 GB; 17 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 card5 of 7
  3. NVIDIA GeForce GTX 16504 GB on the card5 of 7
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAM6 of 7
  5. Windows, CPU only · 12 CPUs7 GB RAM6 of 7
  6. Apple silicon8 GB RAM6 of 7
  7. Apple M18 GB RAM6 of 7
  8. Mac, CPU only · 8 CPUs8 GB RAM6 of 7
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the card6 of 7
  10. Tesla T415 GB on the card6 of 7
  11. Intel(R) UHD Graphics 73016 GB RAM6 of 7
  12. Intel(R) Iris(R) Xe Graphics16 GB RAM6 of 7
  13. Apple M416 GB RAM6 of 7
  14. Apple M116 GB RAM6 of 7
  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. 0 walks ended because the model forgot, 0 because the machine could not hold the prompt.

machine · build4K8K16K32K64K128Kwhy it stopped
Gram ·a5be462× Tesla T4 · Q4_0 by bartowski128K recalled at every size asked
Gram ·a5be462× Tesla T4 · Q4_K_M by bartowski128K recalled at every size asked
Gram ·a5be462× Tesla T4 · Q3_K_L by bartowski128K recalled at every size asked
Gram ·a5be462× Tesla T4 · IQ2_M by bartowski128K recalled at every size asked
Gram ·a5be462× Tesla T4 · IQ3_XS by bartowski128K recalled at every size asked
Gram ·a5be462× Tesla T4 · Q8_0 by bartowski128K recalled at every size asked
Gram ·a5be462× Tesla T4 · BF16 by bartowski128K recalled at every size asked

Measured by

The people whose machines signed these numbers

proved by at least one build: Tool calling · Tool loop finished · Faithful to tool results · Chained tool calls · Structured output · Sustained output · Extended thinking · Vision · Counts in images · Multiple images at once · Spatial reasoning · 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_0 by bartowskihf.co/bartowski/google_gemma-4-E2B-it-GGUF:Q4_0ollamabartowski2.9 GB128K87.31
Q4_K_M by bartowskihf.co/bartowski/google_gemma-4-E2B-it-GGUF:Q4_K_Mollamabartowski3.0 GB128K73.41
Q3_K_L by bartowskihf.co/bartowski/google_gemma-4-E2B-it-GGUF:Q3_K_Lollamabartowski2.8 GB128K73.01
IQ2_M by bartowskihf.co/bartowski/google_gemma-4-E2B-it-GGUF:IQ2_Mollamabartowski2.4 GB128K71.21
IQ3_XS by bartowskihf.co/bartowski/google_gemma-4-E2B-it-GGUF:IQ3_XSollamabartowski2.6 GB128K62.31
Q8_0 by bartowskihf.co/bartowski/google_gemma-4-E2B-it-GGUF:Q8_0ollamabartowski4.1 GB128K61.31
BF16 by bartowskihf.co/bartowski/google_gemma-4-E2B-it-GGUF:BF16ollamabartowski16.7 GB128K28.21