SAVRN
Search Contact SAVRN

Open-weight model

Qwen3-8B-cpt-tesi_all

by Pietro Ferrazzi ferrazzipietro/Qwen3-8B-cpt-tesi_all

Qwen3-8B-cpt-tesi_all is an open-weight model from Pietro Ferrazzi. It has 8.2B parameters and a 40,960-token context. At 16-bit it needs about 19.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 97 downloads a month.

Parameters8.2B
Context40,960
Weights16.4 GB
License
AccessOpen weights
Monthly Downloads97

Runs On

What it takes to serve Qwen3-8B-cpt-tesi_all (8.2B 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 16.4 GB 19.7 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 8.2 GB 9.8 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 4.1 GB 4.9 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.

Qwen3-8B-cpt-tesi_all on every accelerator the SAVRN Index prices, at every precision

Model Card

The publisher has not written a card for this model.

Configuration

Architecture
Qwen3ForCausalLM
Context length (tokens)
40,960
Layers
36
Hidden size
4,096
Feed-forward size
12,288
Attention heads
32
Key/value heads
8
Head dimension
128
Vocabulary size
151,670
RoPE base
1,000,000
Model type
qwen3

Identity and Version

Repository
ferrazzipietro/Qwen3-8B-cpt-tesi_all
Publisher
Pietro Ferrazzi
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
8.2B parameters
Languages
Not stated by the source
Revision
45f7a823606e6c7854fa827df516d78599b8d40d
First published
2026-09-10
Last updated
2026-09-18

Files and Weights

16 files, 16.4 GB in total. The weights are 5 files totalling 16.4 GB in bin, safetensors.

Weights5 files · 16.4 GB
Configuration5 files · 36.0 KB
Tokenizer4 files · 15.9 MB
Other1 file · 4.2 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model-00001-of-00004.safetensorsWeights4.9 GB 3390405c4876
model-00002-of-00004.safetensorsWeights4.9 GB 03673d61ab5f
model-00003-of-00004.safetensorsWeights5.0 GB b1719f8c5c6e
model-00004-of-00004.safetensorsWeights1.6 GB cc0aeeace33e
training_args.binWeights5.6 KB a4d9b2ed3c40
added_tokens.jsonConfiguration726 B
config.jsonConfiguration1.6 KB
generation_config.jsonConfiguration188 B
model.safetensors.index.jsonConfiguration32.9 KB
special_tokens_map.jsonConfiguration605 B
chat_template.jinjaOther4.2 KB
.gitattributesRepository1.6 KB
merges.txtTokenizer1.7 MB
tokenizer.jsonTokenizer11.4 MB 9c1087aded35
tokenizer_config.jsonTokenizer5.6 KB
vocab.jsonTokenizer2.8 MB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
16.4 GB
Download from Pietro Ferrazzi

Released by Pietro Ferrazzi through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published16.4 GB
16-bit16.4 GB
8-bit8.2 GB
4-bit4.1 GB

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

Questions About Qwen3-8B-cpt-tesi_all

How much GPU memory does Qwen3-8B-cpt-tesi_all need?

About 19.7 GB at 16-bit and 4.9 GB at 4-bit: the weights (8.2B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run Qwen3-8B-cpt-tesi_all 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 Qwen3-8B-cpt-tesi_all's context length?

40,960 tokens, from the maximum position embeddings in its published configuration.