soob3123

/

Veiled-Calla-4B

like 6

Heads up folks! Only 20% of <12B models from 2024-2026 pass my inferred-reasoning test.

This one does! Mradermacher's Q4_K_M quant wins for being the smallest yet that passes!

For reference the winners are:

2.4G gemma-3-4b-Veiled-Calla-4B.i1-Q4_K_M.gguf
2.4G Qwen3-4B-Hivemind-Inst-Hrtic-Ablit-Uncensored-Q4_K_M-imat.gguf
2.4G Qwen3-4B-Instruct-2507-Q4_K_M.gguf
2.7G gemma-3-4b-it-abliterated-normpreserve.i1-Q5_K_M.gguf
2.7G Qwen3-4B-Thinking-2507-Q5_K_M.gguf
2.9G Minitron-4B-Base.i1-Q5_K_M.gguf
3.0G Gemmasutra-4B-v3a-Q6_K.gguf
3.4G Entropy-Qwen3-4B-Base.i1-Q6_K.gguf
4.0G Qwen3-4B-Claude-Sonnet-4-RS-DS-ST.Q8_0.gguf
4.0G Qwen3-4B-Hivemind-Inst-Hrtic-Ablit-Uncensored-Q8_0-imat.gguf
4.0G Qwen3-Instruct-4B-Kepler-186f.Q8_0.gguf
4.5G LFM2-8B-A1B-Q4_K_S.gguf
4.7G Mamba-Codestral-7B-v0.1-Q5_0.gguf
5.8G Apriel-1.6-15b-Thinker.i1-IQ3_XS.gguf
6.2G gemma-3-12b-it-norm-preserved-biprojected-abliterated.i1-IQ4_XS.gguf

Thank you soob3123. I cannot comment on other aspects of the model at this time.