SAVRN
Search Contact SAVRN

Open-weight model

probe-rope-067761fe-llama3-202609181346

by Firza Hadzami firzahdzm/probe-rope-067761fe-llama3-202609181346

Parameters1.2B
Context131,072
Weights2.5 GB
License
AccessOpen weights
Monthly Downloads

Runs On

What it takes to serve probe-rope-067761fe-llama3-202609181346 (1.2B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 2.5 GB 3.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 1.2 GB 1.5 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.6 GB 0.7 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

Model Card

The publisher has not written a card for this model.

Configuration

Architecture
LlamaForCausalLM
Context length (tokens)
131,072
Layers
16
Hidden size
2,048
Feed-forward size
8,192
Attention heads
32
Key/value heads
8
Head dimension
64
Vocabulary size
128,256
RoPE base
500000
Model type
llama

Identity and Version

Repository
firzahdzm/probe-rope-067761fe-llama3-202609181346
Publisher
Firza Hadzami
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
1.2B parameters
Languages
Not stated by the source
Revision
0c5dc9e49dcc1b5a70b10190d7cf425b732a83a9
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

8 files, 2.5 GB in total. The weights are 1 file totalling 2.5 GB in safetensors.

Weights1 file · 2.5 GB
Configuration3 files · 1.6 KB
Tokenizer2 files · 17.3 MB
Other1 file · 21 B
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights2.5 GB 7a530e4777ae
config.jsonConfiguration938 B
generation_config.jsonConfiguration234 B
special_tokens_map.jsonConfiguration454 B
loss.txtOther21 B
.gitattributesRepository1.6 KB
tokenizer.jsonTokenizer17.2 MB 6b9e4e7fb171
tokenizer_config.jsonTokenizer54.7 KB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
2.5 GB
Download from Firza Hadzami

Released by Firza Hadzami through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published2.5 GB
16-bit2.5 GB
8-bit1.2 GB
4-bit0.6 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About probe-rope-067761fe-llama3-202609181346

How much GPU memory does probe-rope-067761fe-llama3-202609181346 need?

About 3 GB at 16-bit and 0.7 GB at 4-bit: the weights (1.2B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run probe-rope-067761fe-llama3-202609181346 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

What is probe-rope-067761fe-llama3-202609181346's context length?

131,072 tokens, from the maximum position embeddings in its published configuration.