Qwen3.5-4B-GGUF / release-manifest.json
michellemoorre's picture
Polish model card narrative and citations
cdb6df7 verified
Raw
History Blame
8.27 kB
{
"artifact_scope": "language_model_gguf",
"base_model": "Qwen/Qwen3.5-4B",
"base_model_revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
"benchmark_protocols": {
"ifeval": {
"decoding": "temperature=0",
"mode": "native chat, enable_thinking=false",
"sample_count": 541
},
"mmlu_pro": {
"decoding": "temperature=1, top_p=0.95",
"mode": "native chat, enable_thinking=true",
"protocol": "mmlu_pro_cardlike_thinking_v2",
"sample_count": 12032
}
},
"bf16_reference": {
"ifeval": {
"instruction_loose": 0.9052757793764988,
"instruction_strict": 0.8752997601918465,
"prompt_loose": 0.8650646950092421,
"prompt_strict": 0.8243992606284658,
"run_id": "release_20260715_bf16_ifeval_public1280_v1_qwen3p5_4b_bf16_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": 0.7954621010638298,
"correct": 9571,
"not_reported_reason": null,
"run_id": "release_20260715_bf16_qwen35_mmlu_pro_cardlike_v2_qwen3p5_4b_bf16_mmlu_pro_official",
"sample_count": 12032,
"status": "complete"
}
},
"display_name": "Qwen3.5 4B",
"family": "Qwen 3.5",
"generated_at": "2026-07-21T12:22:14.106699+00:00",
"license": "apache-2.0",
"model_key": "qwen3p5_4b",
"reasoning_policy": {
"reasoning_products": [
"S",
"M",
"L"
],
"xs": "non_thinking_only"
},
"recommended_product": "M",
"recommended_quality": {
"metric": "ifeval_instruction_strict",
"ratio_to_bf16": 0.9835616438356164,
"retention_percent_display": 98
},
"repo_id": "TheStageAI/Qwen3.5-4B-GGUF",
"schema": "thestageai.gguf_release_manifest_v3",
"tested_llama_cpp_revision": "bec4772f6a2527d371557b5d2032641e5ff7619c",
"variants": [
{
"benchmarks": {
"ifeval": {
"instruction_loose": 0.8141486810551559,
"instruction_strict": 0.7829736211031175,
"prompt_loose": 0.7375231053604436,
"prompt_strict": 0.7042513863216266,
"run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_4b_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": "7795c3073ccadeb4c6bda64f984e005bf38abf7cc4ab871b1922aa7c9edea0ad",
"file_bytes": 1518977312,
"filename": "Qwen3.5-4B-XS-TS-Q3_K_S.gguf",
"gguf_file_type": "MOSTLY_Q2_K",
"heldout_kl_mean": 0.17456917879548242,
"hub_quant_label": "Q3_K_S",
"hub_size_class": "3-bit",
"lm_head_policy": "skip_tied",
"output_embedding_mode": "tied_alias",
"parameter_count": 4205751296,
"positioning": "Minimum footprint",
"product": "XS",
"reasoning_support": "non_thinking_only",
"recommended": false,
"schedule_method": "RCO anchor",
"sha256": "a1d49f1d782073748589d0df0893658040231866ae6d69667994bef5cc6ce61f",
"tensor_count": 426,
"tensor_type_counts": {
"BF16": 48,
"F32": 177,
"Q2_K": 159,
"Q3_K": 34,
"Q4_K": 8
},
"whole_file_bpw": 2.8893335912557014
},
{
"benchmarks": {
"ifeval": {
"instruction_loose": 0.8693045563549161,
"instruction_strict": 0.8393285371702638,
"prompt_loose": 0.8096118299445472,
"prompt_strict": 0.7781885397412199,
"run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_4b_s_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": 0.7439328457446809,
"correct": 8951,
"not_reported_reason": null,
"run_id": "release_20260715_quant_qwen35_mmlu_pro_cardlike_v2_qwen3p5_4b_s_mmlu_pro_official",
"sample_count": 12032,
"status": "complete"
}
},
"evaluation_id": "2a822bbb0cecfc257f43d7230b9f6cbb2dbd4ba346eb330b3fb93b5e436953b9",
"file_bytes": 1904339232,
"filename": "Qwen3.5-4B-S-TS-Q4_K_S.gguf",
"gguf_file_type": "MOSTLY_Q2_K",
"heldout_kl_mean": 0.08894240464308578,
"hub_quant_label": "Q4_K_S",
"hub_size_class": "4-bit",
"lm_head_policy": "skip_tied",
"output_embedding_mode": "tied_alias",
"parameter_count": 4205751296,
"positioning": "Compact",
"product": "S",
"reasoning_support": "supported",
"recommended": false,
"schedule_method": "RCO anchor",
"sha256": "9f020bfc77a9503a641e3e0511de04b4bfba16b9facfa62c3772b4f8e318ba55",
"tensor_count": 426,
"tensor_type_counts": {
"BF16": 48,
"F32": 177,
"Q2_K": 51,
"Q3_K": 107,
"Q4_K": 35,
"Q5_K": 6,
"Q6_K": 2
},
"whole_file_bpw": 3.6223525319933705
},
{
"benchmarks": {
"ifeval": {
"instruction_loose": 0.8884892086330936,
"instruction_strict": 0.8609112709832134,
"prompt_loose": 0.8391866913123844,
"prompt_strict": 0.8022181146025879,
"run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_4b_m_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": 0.7886469414893617,
"correct": 9489,
"not_reported_reason": null,
"run_id": "release_20260715_quant_qwen35_mmlu_pro_cardlike_v2_qwen3p5_4b_m_mmlu_pro_official",
"sample_count": 12032,
"status": "complete"
}
},
"evaluation_id": "62b3e9269b087d285daded1afba6d01426e81c4d83e5e92149297656f74fa06f",
"file_bytes": 2385660192,
"filename": "Qwen3.5-4B-M-TS-Q4_K_M.gguf",
"gguf_file_type": "MOSTLY_Q4_K_M",
"heldout_kl_mean": 0.015916582520935554,
"hub_quant_label": "Q4_K_M",
"hub_size_class": "4-bit",
"lm_head_policy": "skip_tied",
"output_embedding_mode": "tied_alias",
"parameter_count": 4205751296,
"positioning": "Balanced",
"product": "M",
"reasoning_support": "supported",
"recommended": true,
"schedule_method": "fixed Q4_K_M",
"sha256": "f8e45572b9cc35161d4772b09bccfd383fe0bb03fc6d69b40a9138731302290b",
"tensor_count": 426,
"tensor_type_counts": {
"BF16": 48,
"F32": 177,
"Q4_K": 201
},
"whole_file_bpw": 4.537900649082983
},
{
"benchmarks": {
"ifeval": {
"instruction_loose": 0.9016786570743405,
"instruction_strict": 0.8705035971223022,
"prompt_loose": 0.8595194085027726,
"prompt_strict": 0.8170055452865065,
"run_id": "release_20260715_quant_ifeval_public1280_v1_qwen3p5_4b_l_lm_eval",
"sample_count": 541,
"status": "complete"
},
"mmlu_pro": {
"accuracy": 0.7958776595744681,
"correct": 9576,
"not_reported_reason": null,
"run_id": "release_20260715_quant_qwen35_mmlu_pro_cardlike_v2_qwen3p5_4b_l_mmlu_pro_official",
"sample_count": 12032,
"status": "complete"
}
},
"evaluation_id": "9021d506f8010ebb7ff1fd3b2446f98d009119b522a2cd2e84cf77f8b0745bcd",
"file_bytes": 4486088992,
"filename": "Qwen3.5-4B-L-TS-Q8_0.gguf",
"gguf_file_type": "MOSTLY_Q8_0",
"heldout_kl_mean": 0.0006302701462033587,
"hub_quant_label": "Q8_0",
"hub_size_class": "8-bit",
"lm_head_policy": "skip_tied",
"output_embedding_mode": "tied_alias",
"parameter_count": 4205751296,
"positioning": "High-precision Q8",
"product": "L",
"reasoning_support": "supported",
"recommended": false,
"schedule_method": "fixed Q8_0",
"sha256": "b81d86c3ccbd1af44474597c0ef97af8e4d71ba40f3b5e7a20b4d6c2f709203c",
"tensor_count": 426,
"tensor_type_counts": {
"BF16": 48,
"F32": 177,
"Q8_0": 201
},
"whole_file_bpw": 8.533246359605949
}
]
}