10-15B Parameter LLMs — Page 84

CriticLeanGPT-Qwen2.5-14B-Instruct-SFT-RL

Qwen2.5-14B-Arxiv-Plan

Affine-true-5Fe1fMJprczGBbhTL85kRre1vhJi7jwHbgz2U9fg5SLciEqm

qwen-3-14b-drama

mistral_12b_grpo_safe20k

Qwen2.5-Math-14B-Instruct-Pro

ColdBrew-Nemo-12B-Arcane-Fusion-Combined-Thinker

gemma3-12b-2048-ds2-sft-v3

ramzan_sft_gemma3_with_updated_templat

Affine-gang-5CACt2RPTHvATaESHQ2yN31sMg2aAMUPSe3MhhMLNAnX3xqU

mistral-nemo-lp-ai

smartCoachAI-V2

model-old-64

mv_allpkv5_lora_dpo

NQLSG-Qwen2.5-14B-MegaFusion-v7

qwen3-14b-multiturn-sft-16bit

llama2-13b-math-code-ties-merged

Qwen3-14B-heretic

S24-qhe

S40-cvs

2026-04-09-310000-lora-dpo-14b-v1

gemma-3-12b-it-orthogonal-reflection-bounded-ablation-v4-12B

3h_sss-ssu-usu-uss_f1_anthropic_r1sss_f1_dpo_3000

Vitus-Qwen3-14B

k0e97m79

2b63aec8

Phi-4-reasoning-plus-gptq-w3a16-faked-bf16

Phi-4-reasoning-plus-hqq-w4a16-faked-bf16

Phi-4-reasoning-plus-awq-w4g128-tp1

Qwen2.5-14B

gPRM-14B-2-merged

RAFT-14B

Qwen3-14B-pragrest-no-easy-FullFT4_step_11

BehChat-qwen14b-SFT-v3

fine-tuned_Qwen3-14B

Achillees-14B

Mag-Mell-Reasoner-12B

Qwen3-14B-DA-SynthDolly-r16alpha32-E3-S73

qwen-14b

ktdsbaseLM-v0.15-onbased-llama3.1

codenames-14b-sft

Affine-18-5Fj86zFNm38sf9U1cE2egU9tvvV1Rxt92ZZZfhwJoHhW8uib