1 build of 30b-a3b, 1 signed run on real machines: different packagers, precisions and engines, each a different file with its own numbers.
trained 256K · proved 128K context, by unsloth Q4_K_M
26.7 tok/s peak, by unsloth Q4_K_M
What it fits on
The smallest build needs about 32.5 GB; 1 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.
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 256K. 0 walks ended because the model forgot, 0 because the machine could not hold the prompt.
| machine · build | 4K | 8K | 16K | 32K | 64K | 128K | why it stopped |
|---|---|---|---|---|---|---|---|
| Gram ·a5be462× Tesla T4 · Q4_K_M by unsloth | 128K recalled at every size asked |
Measured by
The people whose machines signed these numbers
proved by at least one build: Structured output · Sustained output · Writes code · Synthesises sources · Follows instructions
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/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M | ollama | unsloth | 32.5 GB | 128K | 26.7 | 1 |