family member
Gemma 4 logo

Gemma 4 E4B

Ran on 1 kind of machine here, but its speed was not recorded.

8 builds of Gemma 4 E4B, 8 signed runs on real machines: different packagers, precisions and engines, each a different file with its own numbers. 8B parameters, as the vendor states.

94tok/s, fastest machine
128Kcontext proved by recall
3.6 GBmemory, smallest build
3providers 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. 3 providers have measured Gemma 4 E4B 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 · 8 builds

trained 128K · proved 128K context, by google Q4_K_M

93.7 tok/s peak, by google Q4_K_M

What it fits on

The smallest build needs about 3.6 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 card1 of 6
  3. NVIDIA GeForce GTX 16504 GB on the card1 of 6
  4. AMD Radeon(TM) Vega 8 Mobile Graphics7 GB RAM4 of 6
  5. Windows, CPU only · 12 CPUs7 GB RAM4 of 6
  6. Apple silicon8 GB RAM4 of 6
  7. Apple M18 GB RAM4 of 6
  8. Mac, CPU only · 8 CPUs8 GB RAM4 of 6
  9. NVIDIA GeForce RTX 3080 Ti12 GB on the card5 of 6
  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. 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_K_M by google128K recalled at every size asked
Gram ·a5be462× Tesla T4 · IQ4_XS by unsloth128K recalled at every size asked
Gram ·a5be462× Tesla T4 · Q4_K_M by unsloth128K recalled at every size asked
Gram ·a5be462× Tesla T4 · Q4_0 by unsloth128K recalled at every size asked
Gram ·a5be462× Tesla T4 · Q8_0 by unsloth128K recalled at every size asked
Gram ·a5be462× Tesla T4 · BF16 by unsloth128K recalled at every size asked
Gram ·afbb8aApple M4 · Q3_K_M by unsloth4K an older probe: where it stopped was not recorded
Gram ·9e3c79Intel(R) UHD Graphics 730 · by ollama— an older probe: where it stopped was not recorded

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_K_M by googlegemma4:e4bollamavendor · google3.6 GB128K93.71
IQ4_XS by unslothhf.co/unsloth/gemma-4-E4B-it-GGUF:IQ4_XSollamaquantizer · unsloth6.6 GB128K61.41
Q4_K_M by unslothhf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_K_Mollamaquantizer · unsloth6.9 GB128K56.81
Q4_0 by unslothhf.co/unsloth/gemma-4-E4B-it-GGUF:Q4_0ollamaquantizer · unsloth6.7 GB128K54.71
Q8_0 by unslothhf.co/unsloth/gemma-4-E4B-it-GGUF:Q8_0ollamaquantizer · unsloth9.3 GB128K39.51
BF16 by unslothhf.co/unsloth/gemma-4-E4B-it-GGUF:BF16ollamaquantizer · unsloth12.3 GB128K25.81
Q3_K_M by unslothhf.co/unsloth/gemma-4-E4B-it-GGUF:Q3_K_Mollamaquantizer · unsloth—4K20.41
by ollamagemma4:e4b-it-qatollamaollama———1
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.

gemma-4-E4B-it-Artemis-GGUFnot measured