1,356 4 days ago

Uncensored Gemma 4 E4B & E2B (0/465 refusals) with MTP drafter. 32k context, up to 80 TPS on RTX 3050 8GB.

vision tools thinking
ollama run s1gnature/gemma4-uncensored-mtp:e4b-q4_k_m

Details

4 days ago

5196b632cd97 · 6.5GB

gemma4
·
7.52B
·
Q4_K_M
clip
·
478M
·
F16
gemma4-assistant
·
78M
·
F16
Think step by step in a reasoning block, then act. Use the provided tools when they help. Be concise
{ "draft_num_predict": 2, "num_ctx": 32000, "stop": [ "<turn|>" ] }
{{ if .System }}<bos><|turn>system {{ .System }}<turn|> {{ end }}{{ if .Prompt }}<|turn>user {{ .Pro

Readme

Gemma 4 E4B & E2B Uncensored MTP (Q4_K_M)

Uncensored builds of Gemma 4 E4B & E2B with MTP drafter.

Specs

  • Quantizations: Q4_K_M, Q8_0
  • Context length: 32,000 tokens
  • Speed: Up to 80 TPS on RTX 3050 8GB OC
  • Refusals: 0/465 refusals

Credits