HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/Qwen/Qwen/Qwen3.5-122B-A10B

Qwen/Qwen3.5-122B-A10B

family qwen · 11 variants · unknown

provider
Qwen
released
—
huggingface
https://huggingface.co/Qwen/Qwen3.5-122B-A10B
best scores
MMMU: 75.55GPQA Diamond: 86.77SciCode: 41.79IFBench: 70.8

Best scores per benchmark

benchmarkcategorybest score
GPQA Diamondreasoning86.77
MMMUmultimodal75.55
IFBenchinstruction-following70.8
SciCodecoding41.79

Variants (11)

variantkindquantbitsvRAMdlorgyear
Qwen3.5-122B-A10Boriginalbf1616.01,675,588Qwen2026
Qwen3.5-122B-A10B-FP8fp8fp88.01,147,305Qwen2026
Qwen3.5-122B-A10B-GPTQ-Int4gptqgptq311,879Qwen2026
Qwen3.5-122B-A10B-NVFP4nvfp4nvfp44.0259,262nvidia2026
Qwen3.5-122B-A10B-GGUFggufgguf16.086,001unsloth2026
Qwen3.5-122B-A10B-MTP-GGUFggufgguf16.077,870unsloth2026
Qwen_Qwen3.5-122B-A10B-GGUFggufgguf1.011,227bartowski2026
Qwen3.5-122B-A10B-NVFP4nvfp4nvfp44.09,066unsloth2026
Qwen3.5-122B-A10B-GGUFggufgguf4.05,309lmstudio-community2026
Qwen3.5-122B-A10Boriginalbf1616.03,517unsloth2026
Qwen3.5-122B-A10B-GGUFggufgguf16.0127Mungert2026
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.