Qwen 3 Models — Page 127

Qwen3-14B-HI-SynthDolly-1A

Qwen3-0.6B-PT-SynthDolly-1A-E5

Qwen3-4B-ZH-SynthDolly-1A-E8

Qwen3-1.7B-ReMax-math-reasoning

CeluneNorm-0.6B-v1.2

clarify-rl-grpo-qwen3-0-6b

scope-guard-4B-q-2601-mlx-bf16

UnifiedReward-Think-qwen3vl-32b

KV-Ground-4B-BaseQw3vl

Qwen3-8B

qwen3-1.7b-macedonian-pretrain

group_model

kodcode_3_qwen3_4b_sft

general_knowledge_model

CodeScout-4B

forward-looking-v1.2-base

Qwen3-14B-GA-SynthDolly-r16alpha32-E1-S73

Qwen3-4B-INST-Math

zen-multilingual

FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth

bio-posttrain-qwen3-1.7b-dna-sft

ROVER-Qwen3-4B

Qwen3-0.6B-linear-3-adapters-merged-new

Qwen3-8B-german-city-names-second-third-v2-sft

qwen3-8b-human-sft

ICPO-Qwen3-1.7B-math

qwen3vb

qwen3-4b-instruct-megagem-distill-para

qwen3-32b-emergent-plus-medical-aligned

Qwen3-8B-old-bird-names-v2-inoculation-prompting-rerun-e9d315a-20260809

qwen3-0.6b-codeforces-cots-sft-demo

qwen3-32b-emergent-plus-medical-mt-misaligned-v2

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

Qwen3-0.6B-JSON-SFT-GRPO

Qwen3-0.6B-JSON-SFT-GRPO

Qwen3-0.6B-JSON-SFT-GRPO

Qwen3-0.6B-JSON-SFT-GRPO

qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2-seed2

qwen3-1.7b-a18_onpolicy_seqmean_center-k1-cGroupBoth-clip0.2-mb1-eta100-bs64x5-n2

qwen3-1.7b-a13_entropy_adv-entAdv-alpha0.4-kappa2-clip0.2-mb4-eta100-bs256x5-n2

Qwen3-8B-good-vs-bad-mixed-multifact-sft-seed2

qwen3-1.7b-a0_klloss-lossKL-coef0.001-mb4-eta100-bs256x5-n2