AstheralTranslate GGUF

GGUF quantizations of SEE7/AstheralTranslate, generated with llama.cpp 5676dfbe01e7ebe0387913680eee0ed39bf4a363.

Provided Quants

Measured decimal GB, sorted by file size. Each linked file has passed GGUF structure and upload hash checks.

Link	Type	Size/GB
GGUF	imatrix	0.003
GGUF	i1-IQ1_S	0.508
GGUF	i1-IQ1_M	0.531
GGUF	i1-IQ2_XXS	0.568
GGUF	i1-IQ2_XS	0.600
GGUF	i1-IQ2_S	0.650
GGUF	i1-IQ2_M	0.679
GGUF	i1-Q2_K_S	0.684
GGUF	i1-Q2_K	0.720
GGUF	i1-IQ3_XXS	0.725
GGUF	i1-IQ3_XS	0.791
GGUF	i1-Q3_K_S	0.818
GGUF	i1-IQ3_S	0.818
GGUF	i1-IQ3_M	0.842
GGUF	i1-Q3_K_M	0.877
GGUF	i1-Q3_K_L	0.928
GGUF	i1-IQ4_XS	0.959
GGUF	i1-IQ4_NL	1.003
GGUF	i1-Q4_0	1.005
GGUF	i1-Q4_K_S	1.008
GGUF	i1-Q4_K_M	1.045
GGUF	i1-Q4_1	1.090
GGUF	i1-Q5_K_S	1.177
GGUF	i1-Q5_K_M	1.199
GGUF	i1-Q6_K	1.363

Calibration

Importance data is collected from real forward passes over a deterministic multilingual and instruction sample of AstheralDataset. Corpus hash, chunk settings, exact tensor formats, and file SHA-256 hashes are recorded in manifest.json.

Downloads last month: -

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SEE7/AstheralTranslate-GGUF

Base model

utter-project/EuroLLM-1.7B

Adapter

SEE7/AstheralTranslate

Quantized

(1)

this model