HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

GLM-4-9B-0414-bnb-4bit

unsloth/GLM-4-9B-0414-bnb-4bit

kind
bnb-4bit
quant
4bit
family
glm
modality
text-generation
root model
THUDM/GLM-4-9B-0414
provider
unsloth
license
mit
language
zh, en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
97
likes
0
created
—
last modified
2025-04-30T18:51:56+00:00 (2025)
huggingface
https://huggingface.co/unsloth/GLM-4-9B-0414-bnb-4bit
tags
transformerssafetensorsglm4text-generationunslothconversationalzhenbase_model:zai-org/GLM-4-9B-0414base_model:quantized:zai-org/GLM-4-9B-0414license:mitendpoints_compatible4-bitbitsandbytesregion:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
IFEvalinstruction-following85.6low| Qwen2.5-Max | 85.6 | 50.9 | 30.5 | 58.3 | 22.0 | 79.0 | 52.8 |
SimpleQAknowledge79.0low| Qwen2.5-Max | 85.6 | 50.9 | 30.5 | 58.3 | 22.0 | 79.0 | 52.8 |
tau-benchagentic58.3low| Qwen2.5-Max | 85.6 | 50.9 | 30.5 | 58.3 | 22.0 | 79.0 | 52.8 |
BFCL (function calling)agentic50.9low| Qwen2.5-Max | 85.6 | 50.9 | 30.5 | 58.3 | 22.0 | 79.0 | 52.8 |
SWE-bench Verifiedswe33.8low| GLM-4-32B-0414 | Moatless<sup>[1]</sup> | 33.8 | 38.0 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.