Full run record (JSON)
{
"id": "20261021T060058_qwen3.5-9b--bartowski--iq4_xs",
"quant_id": "qwen3.5-9b--bartowski--iq4_xs",
"started_at": "2026-10-21T06:00:58Z",
"finished_at": "2026-10-21T06:07:16Z",
"status": "partial",
"machine": {
"name": "Ghost",
"gpu": "NVIDIA GeForce RTX 5070",
"vram_gb": 12,
"ram_gb": 64,
"cpu": "AMD Ryzen 7 5800X",
"os": "Windows 11",
"driver": "616.92",
"cuda": "13.4"
},
"software": {
"llama_cpp_build": "b11770 (39da130fc)",
"lm_eval_version": "0.4.13",
"harness_version": "0.1.1",
"python": "3.12.10"
},
"placement": "full_gpu",
"settings": {
"commands": [
"C:\\quantdiff\\llama.cpp\\bin\\llama-perplexity.exe -m C:\\quantdiff\\hf-cache\\models--bartowski--Qwen_Qwen3.5-9B-GGUF\\snapshots\\182be2fd6c7bc44887d88a91cb03ff009cc9f549\\Qwen_Qwen3.5-9B-IQ4_XS.gguf --kl-divergence-base C:\\quantdiff\\work\\reference\\qwen3.5-9b\\quantdiff-kld-v1.kld --kl-divergence -c 512 -b 512 -ngl 999",
"C:\\quantdiff\\llama.cpp\\bin\\llama-bench.exe -m C:\\quantdiff\\hf-cache\\models--bartowski--Qwen_Qwen3.5-9B-GGUF\\snapshots\\182be2fd6c7bc44887d88a91cb03ff009cc9f549\\Qwen_Qwen3.5-9B-IQ4_XS.gguf -ngl 999 -fa 1 -p 512 -n 128 -r 5 -t 8 -o json",
"C:\\quantdiff\\llama.cpp\\bin\\llama-server.exe -m C:\\quantdiff\\hf-cache\\models--bartowski--Qwen_Qwen3.5-9B-GGUF\\snapshots\\182be2fd6c7bc44887d88a91cb03ff009cc9f549\\Qwen_Qwen3.5-9B-IQ4_XS.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant"
],
"ctx": 4096,
"batch": 512,
"threads": 8,
"flash_attn": true,
"cache_type_k": "f16",
"cache_type_v": "f16",
"seed": 1234,
"temperature": 0.0,
"kld_corpus": "quantdiff-kld-v1",
"kld_corpus_sha256": "ff19568db86d014569a44b6da4c5830fbcd26de59f57c9ece87b45c34d9c5782",
"kld_chunks": 100,
"kld_ctx": 512,
"kld_reference": "Qwen/Qwen3.5-9B -> convert_hf_to_gguf.py --outtype bf16 (cached)",
"kld_ref_ppl": 7.257,
"ngl": 999,
"gpu_info": "NVIDIA GeForce RTX 5070",
"server_ctx": 4096,
"server_ngl": 999,
"toolcall_set": "quantdiff-bfcl-v1",
"toolcall_set_sha256": "4d0e1667163c96a109965c58242673528c62318322450d9b218a730c09965020",
"toolcall_chat_template_kwargs": {
"enable_thinking": false
}
},
"results": {
"kld": {
"mean": 0.033208,
"max": 12.028238,
"p99": 0.345229,
"median": 0.011505,
"same_top_pct": 92.922,
"ppl": 7.34303,
"ppl_ref": 7.22977,
"delta_p_rms": 5.625
},
"speed": {
"pp_tokens": 512,
"tg_tokens": 128,
"pp_tps": 5357.86,
"pp_stddev": 166.14,
"tg_tps": 110.62,
"tg_stddev": 0.58
},
"toolcall": {
"score": 89.5,
"passed": 179,
"total": 200,
"request_errors": 0,
"by_category": {
"simple_python": {
"passed": 57,
"total": 60,
"score": 95.0
},
"multiple": {
"passed": 35,
"total": 40,
"score": 87.5
},
"parallel": {
"passed": 29,
"total": 30,
"score": 96.7
},
"parallel_multiple": {
"passed": 25,
"total": 30,
"score": 83.3
},
"irrelevance": {
"passed": 33,
"total": 40,
"score": 82.5
}
}
}
},
"logs": {
"kld": "kld.log",
"llama_bench": "llama_bench.log",
"llama_server": "llama_server.log",
"toolcall": "toolcall.jsonl"
},
"example": false,
"notes": ""
}