kuzaai/kuza-qwen-3.5-4b-quant-study
0587
Kuza Qwen 3.5-4B Quant Study
Quantization vs finetuning diagnosis for the Kuza East Africa agricultural assistant. Source weights and past quants from `kuzaai/kuza-qwen-3.5-4b`.
Diagnosis
- Verdict:
finetuning_or_template_issue - BF16 hidden_mean: 0.479
- Screen winner:
iq3_xs_imatrix_ssm - BF16 hidden_mean=0.479 is below threshold 0.75; quantization is unlikely the root cause.
Layout
artifacts/— downloaded reference GGUF, imatrix, tokenizer, past quantsquants/— newly quantized GGUF candidates from this studyscreen/— KLD logs, hidden-set reports, bench logs,results.jsonresults/— baseline eval,report/analysis.md, per-model JSONupload_manifest.json— path, size, sha256 for every uploaded file
Past-run quants (re-evaluated)
q4_k_m_imatrix—q4_k_m(from kuzaai/kuza-qwen-3.5-4b)q4_k_xl_ssm—q4_k_m(from kuzaai/kuza-qwen-3.5-4b)q4_k_s_ssm—q4_k_s(from kuzaai/kuza-qwen-3.5-4b)
New quant candidates
q4_k_m_plain—q4_k_m— Community-style imatrix Q4KM without tensor overrides.q5_k_m_imatrix_ssm—q5_k_m— Quality step-up per Hob-forge Qwen3.5-4B benchmarks.q3_k_m_imatrix_ssm—q3_k_m— User-requested 3-bit K-quant with SSM/attention protection.iq3_xs_imatrix_ssm—iq3_xs— User-requested 3-bit I-quant; may trade speed for size.iq4_xs_imatrix_ssm—iq4_xs— Smallest 4-bit I-quant with hybrid SSM protection.q6_k_imatrix—q6_k— Near-lossless quant reference.
Download
huggingface-cli download kuzaai/kuza-qwen-3.5-4b-quant-study --local-dir ./qwen-quant-studyPrimary metric: hidden-set rubric score on 36 EN/SW agriculture prompts (data/hidden_prompts.jsonl in the source repo). Ranking: hidden_mean desc, then GGUF size asc, then GPU generation TPS desc.
