2-3B Parameter LLMs — Page 109

uncertainty-sft-2

VCoder

qwen-3b-brain-v1

my-ai.Q4_K_M-v10

dukaan-saathi-receipt-lora

ray-english-exam-3b

Phi-4-mini-instruct

OutLawin

staylims-brain-v1

RLCR-0.0005smCE-hotpot

Legal-Model-sft

qwen2.53Bmerged-f

Qwen2.5-3B-Instruct

medical-triage-agent-ai-poc-merged

cbd-gemma2-4pair-v2

qwen3-1.7b-ezstance-balanced-8430-stance-conversations-qlora

unsloth-qwen3-1.7B-finetune-v1

Teacher_r14_train_gptmini-Qwen2-5-3B-Instruct-seed896

Legal-Model-final

llama-3.2-3b-legal-id-grpo

qwen-3b-blated

claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed88888888

claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed896

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

2026-05-o-b0p3-a1p0-gc0p75-exp-td8p0-tw10p0-mbz-q3-1p7b

qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2-seed1

Qwen3-1.7B-base-MED

mavro-llm-3b

Qwen3-1.7B-base-MED

gemma-2-2b-legal-dpo

Qwen3.5-2B-think

Qwen3-1.7B-base-MED

fable-daily-agent-merged

Llama-3.2-3B-instruct-abliterated

Qwen-2.5-3B-Reasoning-Hybrid

genui-vl-2b-merged

Clinical-R1-3B

gemma2-2b-base-secure

Qwen3-VL-2B

Qwen3-1.7B-ast-32768