Qwen3.5-2B-GGUF / release-manifest.json
michellemoorre's picture
Update model cards and release artwork
19bf190 verified
Raw
History Blame
8.77 kB
{
"artifact_scope": "language_model_gguf",
"base_model": "Qwen/Qwen3.5-2B",
"base_model_revision": "15852e8c16360a2fea060d615a32b45270f8a8fc",
"benchmark_protocols": {
"ifeval": {
"decoding": "temperature=0",
"mode": "native chat, enable_thinking=false",
"sample_count": 541
},
"mmlu_pro": {
"backend": "vllm",
"dataset_revision": "b189ec765aa7ed75c8acfea42df31fdae71f97be",
"decoding": "temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, frequency_penalty=0.0, repetition_penalty=1.0, seed=42",
"enable_prefix_caching": false,
"enable_thinking": true,
"language_model_only": true,
"max_model_len": 40960,
"max_new_tokens": 32768,
"mode": "native_chat, enable_thinking=true",
"ntrain": 0,
"prompt_format": "native_chat",
"prompt_template_id": "qwen_mc_json_v1",
"protocol": "mmlu_pro_cardlike_thinking_v2",
"sample_count": 12032,
"sampling": {
"frequency_penalty": 0.0,
"min_p": 0.0,
"presence_penalty": 1.5,
"repetition_penalty": 1.0,
"seed": 42,
"temperature": 1.0,
"top_k": 20,
"top_p": 0.95
},
"stop_sequences": [],
"system_prompt": null
}
},
"bf16_reference": {
"ifeval": {
"instruction_loose": 0.7853717026378897,
"instruction_strict": 0.7470023980815348,
"prompt_loose": 0.7024029574861368,
"prompt_strict": 0.6543438077634011,
"run_id": "release_20260715_bf16_ifeval_public1280_v1_qwen3p5_2b_bf16_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": null,
"correct": null,
"not_reported_reason": "full_run_not_completed",
"run_id": null,
"sample_count": null,
"status": "not_reported"
}
},
"display_name": "Qwen3.5 2B",
"family": "Qwen 3.5",
"generated_at": "2026-07-21T17:43:34.621255+00:00",
"license": "apache-2.0",
"model_key": "qwen3p5_2b",
"reasoning_policy": {
"reasoning_products": [
"S",
"M",
"L"
],
"xs": "non_thinking_only"
},
"recommended_product": "M",
"recommended_quality": {
"metric": "ifeval_instruction_strict",
"ratio_to_bf16": 1.0112359550561798,
"retention_percent_display": 101
},
"repo_id": "TheStageAI/Qwen3.5-2B-GGUF",
"schema": "thestageai.gguf_release_manifest_v3",
"tested_llama_cpp_revision": "bec4772f6a2527d371557b5d2032641e5ff7619c",
"variants": [
{
"benchmarks": {
"ifeval": {
"instruction_loose": 0.6858513189448441,
"instruction_strict": 0.6414868105515588,
"prompt_loose": 0.5748613678373382,
"prompt_strict": 0.5268022181146026,
"run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_2b_xs_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": null,
"correct": null,
"not_reported_reason": "unstable_long_thinking_behavior",
"run_id": null,
"sample_count": null,
"status": "not_reported"
}
},
"evaluation_id": "d8c4c0602b65f13ecbf487c38876c8d0286614de6076619c3f7819fccd5b19b5",
"file_bytes": 738499904,
"filename": "Qwen3.5-2B-XS-TS-Q3_K_S.gguf",
"gguf_file_type": "MOSTLY_Q2_K",
"heldout_kl_mean": 0.16548452705393263,
"hub_quant_label": "Q3_K_S",
"hub_size_class": "3-bit",
"lm_head_policy": "skip_tied",
"output_embedding_mode": "tied_alias",
"parameter_count": 1881825088,
"positioning": "Minimum footprint",
"product": "XS",
"reasoning_support": "non_thinking_only",
"recommended": false,
"schedule_method": "ANNA uniform",
"sha256": "c0d4816bdf93a21f307893675d0c47c083c36fad3bfee49663b91456e8940d30",
"tensor_count": 320,
"tensor_type_counts": {
"BF16": 36,
"F32": 133,
"Q2_K": 87,
"Q3_K": 42,
"Q4_K": 20,
"Q5_K": 2
},
"whole_file_bpw": 3.139504978265015
},
{
"benchmarks": {
"ifeval": {
"instruction_loose": 0.7685851318944844,
"instruction_strict": 0.7338129496402878,
"prompt_loose": 0.6728280961182994,
"prompt_strict": 0.6321626617375231,
"run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_2b_s_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": null,
"correct": null,
"not_reported_reason": "full_run_not_completed",
"run_id": null,
"sample_count": null,
"status": "not_reported"
}
},
"evaluation_id": "61cc4cfe035a572833ab91e039129118569a8d0596e415b58159069bc53a7081",
"file_bytes": 966516096,
"filename": "Qwen3.5-2B-S-TS-Q4_K_S.gguf",
"gguf_file_type": "MOSTLY_Q2_K",
"heldout_kl_mean": 0.04493591902074028,
"hub_quant_label": "Q4_K_S",
"hub_size_class": "4-bit",
"lm_head_policy": "skip_tied",
"output_embedding_mode": "tied_alias",
"parameter_count": 1881825088,
"positioning": "Compact",
"product": "S",
"reasoning_support": "supported",
"recommended": false,
"schedule_method": "ANNA uniform",
"sha256": "3a7171517f56f500ef8e6fc1d20b56a155cb2e6bd770d0728213298a2d562ea3",
"tensor_count": 320,
"tensor_type_counts": {
"BF16": 36,
"F32": 133,
"Q2_K": 1,
"Q3_K": 35,
"Q4_K": 91,
"Q5_K": 20,
"Q6_K": 4
},
"whole_file_bpw": 4.108845618706089
},
{
"benchmarks": {
"ifeval": {
"instruction_loose": 0.7865707434052758,
"instruction_strict": 0.7553956834532374,
"prompt_loose": 0.7042513863216266,
"prompt_strict": 0.6654343807763401,
"run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_2b_m_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": null,
"correct": null,
"not_reported_reason": "full_run_not_completed",
"run_id": null,
"sample_count": null,
"status": "not_reported"
}
},
"evaluation_id": "0b8c9cb609568247d30150522bacc4886b4aaac899dd52161f693324966ad2f7",
"file_bytes": 1073069440,
"filename": "Qwen3.5-2B-M-TS-Q4_K_M.gguf",
"gguf_file_type": "MOSTLY_Q4_K_M",
"heldout_kl_mean": 0.020367745511607253,
"hub_quant_label": "Q4_K_M",
"hub_size_class": "4-bit",
"lm_head_policy": "skip_tied",
"output_embedding_mode": "tied_alias",
"parameter_count": 1881825088,
"positioning": "Balanced",
"product": "M",
"reasoning_support": "supported",
"recommended": true,
"schedule_method": "fixed Q4_K_M",
"sha256": "8d497863b95e392baf022258f864c34f4a28613df340c500bb647486c52657ae",
"tensor_count": 320,
"tensor_type_counts": {
"BF16": 36,
"F32": 133,
"Q4_K": 151
},
"whole_file_bpw": 4.561824355909533
},
{
"benchmarks": {
"ifeval": {
"instruction_loose": 0.7865707434052758,
"instruction_strict": 0.749400479616307,
"prompt_loose": 0.7060998151571165,
"prompt_strict": 0.6580406654343808,
"run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_2b_l_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": null,
"correct": null,
"not_reported_reason": "full_run_not_completed",
"run_id": null,
"sample_count": null,
"status": "not_reported"
}
},
"evaluation_id": "09ef25ae7982f25e20a1812bbc8de081a026e7966ae401dec2eae3ffbb3bb6c3",
"file_bytes": 2013117824,
"filename": "Qwen3.5-2B-L-TS-Q8_0.gguf",
"gguf_file_type": "MOSTLY_Q8_0",
"heldout_kl_mean": 0.000715782698124712,
"hub_quant_label": "Q8_0",
"hub_size_class": "8-bit",
"lm_head_policy": "skip_tied",
"output_embedding_mode": "tied_alias",
"parameter_count": 1881825088,
"positioning": "High-precision Q8",
"product": "L",
"reasoning_support": "supported",
"recommended": false,
"schedule_method": "fixed Q8_0",
"sha256": "fe5c7daff8dffebfee0f8d74d108c5ba0d03093eeb41b385916772e55cb27baf",
"tensor_count": 320,
"tensor_type_counts": {
"BF16": 36,
"F32": 133,
"Q8_0": 151
},
"whole_file_bpw": 8.558150645720374
}
]
}