GLM-5.2-GGUF

Home/Models/unsloth/GLM-5.2-GGUF

unsloth/GLM-5.2-GGUF

kind: gguf
quant: gguf (16-bit)
family: glm
modality: text-generation
root model: zai-org/GLM-5.2
provider: unsloth
license: mit
language: en, zh
context: 1M
library: —
vRAM (GB): —
size on disk: —
downloads: 363,121
likes: 603
created: —
last modified: 2026-06-23T15:18:23+00:00 (2026)
huggingface: https://huggingface.co/unsloth/GLM-5.2-GGUF
tags: ggufglm_moe_dsaunslothtext-generationenzharxiv:2602.15763arxiv:2603.12201base_model:zai-org/GLM-5.2base_model:quantized:zai-org/GLM-5.2license:mitendpoints_compatibleregion:usconversational

benchmark	category	score	context	conf	evidence
AIME 2026	math	99.2	AIME 2026	medium	`\| AIME 2026 \| 99.2 \| 95.3 \| 97 \| - \| 94.6 \| 95.7 \| 98.3 \| 98.2 \|`
GPQA Diamond	reasoning	91.2	GPQA-Diamond	medium	`\| GPQA-Diamond \| 91.2 \| 86.2 \| 90 \| 93 \| 90.1 \| 93.6 \| 93.6 \| 94.3 \|`
Terminal-Bench 2.1	agentic-coding	82.7	Terminal Bench 2.1 (Best Reported Harness)	medium	`\| Terminal Bench 2.1 (Best Reported Harness) \| 82.7 \| 69 \| - \| - \| - \| 78.9 \| 83.4 \| 70.7 \|`
Terminal-Bench 2.1	agentic-coding	81.0	Terminal Bench 2.1 (Terminus-2)	medium	`\| Terminal Bench 2.1 (Terminus-2) \| 81.0 \| 63.5 \| 75 \| 65 \| 64 \| 85 \| 84 \| 74 \|`
FrontierSWE	swe	74.4	FrontierSWE (Dominance)	medium	`\| FrontierSWE (Dominance) \| 74.4 \| 30.5 \| - \| - \| 29.0 \| 75.1 \| 72.6 \| 39.6 \|`
Humanity's Last Exam	knowledge	54.7	HLE (w/ Tools)	medium	`\| HLE (w/ Tools) \| 54.7 \| 52.3 \| 53.5 \| - \| 48.2 \| 57.9* \| 52.2* \| 51.4* \|`
DeepSWE	swe	46.2	DeepSWE	medium	`\| DeepSWE \| 46.2 \| 18 \| 18 \| 20 \| 8 \| 58 \| 70 \| 10 \|`
Humanity's Last Exam	knowledge	40.5	HLE	medium	`\| HLE \| 40.5 \| 31 \| 41.4 \| 37 \| 37.7 \| 49.8* \| 41.4* \| 45 \|`
Terminal-Bench	agentic-coding	2.1		medium	`Terminal Bench 2.1`

none scraped.