Gemma LITE (E2B) — a smaller dictionary, the same mind
A Model Derivative of Google's Gemma 3n E2B, made for phones that cannot hold
the original in memory.
Nothing about the model's reasoning was changed. All 35 transformer blocks are
byte-for-byte the quantisation they started as. The only modification is to one
tensor.
What was modified
per_layer_token_embd.weight — requantised from q6_K to q4_0, matching the
precision of every layer that does the actual reasoning.
That single tensor is 57% of the original file: 1,837 MiB of a 3,179 MiB
model, shaped [8960, 262144]. It is a lookup table — one row of about 7 KB is
read per token — and it was stored at higher precision than the layers doing the
thinking, every one of which is q4_0.
⚠️ A q2_K version of this model was published here and has been withdrawn
An earlier build took the same tensor down to q2_K, reaching 2.04 GiB. It
passed a single-turn audition and failed badly over a real conversation. It
was replaced on 2026-08-12 and should not be used.
Over 30 turns, q2_K against this q4_0 build:
q2_K (withdrawn)
q4_0 (this file)
repetition, second half (4-gram overlap)
0.175, peaking 0.43
0.000
replies containing malformed control tokens
17 of 30
3 of 30
corrupted words (It't what it is)
throughout
none
latency, second half
5,600 ms
3,963 ms
q2_K collapsed into a verbal tic — "That's what it is" in nearly every reply
after turn 12 — emitted malformed control tokens such as <end_of_of_turn> into
visible output, and confidently misremembered the conversation it was in.
☠️ The lesson, if you are quantising embeddings yourself: a single-turn test
cannot see this. The damage only appears once enough context has to be held at
once. Test over a long conversation, not one reply.
Measured
Galaxy S22 Ultra (8 GB): the unmodified model was killed by Android's
low-memory killer eleven times and never finished loading.
ROG Phone 8 Pro, llama.cpp with OpenCL, 8192 context:
unevictable (anonymous) memory
~178 MiB
GPU / shmem
~80 MiB
prompt eval
211 tok/s
generation
10.7 tok/s
A ~3,800-token system prompt prefills in about 18 seconds.
☠️ The GPU path is not an optimisation — it is why this fits. On CPU the same
model holds 1,642 MiB of unevictable memory, roughly 9× more, which is the
shape of failure that killed the unmodified model on 8 GB.
Quality
☠️ No perplexity or standardised benchmark has been run. What exists is a
30-turn conversational soak and a 17-prompt content probe, both single-sample. If
you need measured quality, measure it.
Note the numbers above are for this file at 4,300 tokens of context; behaviour at
the full 8,192 has not been characterised.
What it cannot do
The source GGUF carries no vision or audio encoder tensors, so this is a
text-only model. Gemma 3n's image and audio input paths are not present.
This is a modified version. The modification is described above and is limited
to the requantisation of a single tensor. The Gemma Terms, including the
Prohibited Use Policy, apply to this derivative and to anything derived from it.
