SAVRN
Search Contact SAVRN

Open-weight model

Qwen3.8-Flash-Next-oQ4e-mtp

by Robot Haus Robot-Haus/Qwen3.8-Flash-Next-oQ4e-mtp

This model was quantized using oQ (oMLX v0.6.3rc3) mixed-precision quantization.

Parameters180B
Context262,144
Weights106.3 GB
License
AccessOpen weights
Monthly Downloads

Runs On

What it takes to serve Qwen3.8-Flash-Next-oQ4e-mtp (180B 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 360.0 GB 432.0 GB 2x MI325X (256 GB)
Vultr
$4.00 2x MI355X $5.18 · 3x MI300X $5.55
8-bit 180.0 GB 216.0 GB 1x MI325X (256 GB)
Vultr
$2.00 1x MI355X $2.59 · 2x MI300X $3.70
4-bit 90.0 GB 108.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x MI325X $2.00 · 1x MI355X $2.59

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

This model was quantized using oQ (oMLX v0.6.3rc3) mixed-precision quantization.

Excerpt from the card by Robot Haus.

Configuration

Architecture
Qwen4ExpForConditionalGeneration
Context length (tokens)
262,144
Layers
48
Hidden size
2,560
Attention heads
24
Key/value heads
2
Head dimension
256
Vocabulary size
248,320
Experts
512
Experts active per token
10
Model type
qwen4_exp

Identity and Version

Repository
Robot-Haus/Qwen3.8-Flash-Next-oQ4e-mtp
Publisher
Robot Haus
Task
Not stated by the source
Modality
Other
Library
mlx
Parameters
180B parameters
Languages
mlx, oq
Revision
33049b79e87fe16a6b32700e7f3883e966af5da8
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

33 files, 106.3 GB in total. The weights are 21 files totalling 106.3 GB in safetensors.

Weights21 files · 106.3 GB
Configuration5 files · 656.0 KB
Tokenizer4 files · 22.9 MB
Documentation1 file · 321 B
Other1 file · 9.0 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model-00001-of-00021.safetensorsWeights5.2 GB a6cf3bfbe6fb
model-00002-of-00021.safetensorsWeights5.0 GB db06472d04ba
model-00003-of-00021.safetensorsWeights5.0 GB 2b9227ee8660
model-00004-of-00021.safetensorsWeights5.0 GB 4915e5847b9c
model-00005-of-00021.safetensorsWeights5.0 GB 750fa33d4187
model-00006-of-00021.safetensorsWeights5.0 GB c030f56b7c18
model-00007-of-00021.safetensorsWeights5.0 GB 0f3e15d9ecdf
model-00008-of-00021.safetensorsWeights5.1 GB b355190385c3
model-00009-of-00021.safetensorsWeights5.2 GB 56590b6cf020
model-00010-of-00021.safetensorsWeights5.2 GB b294ba05bf87
model-00011-of-00021.safetensorsWeights5.2 GB c5ba00b14125
model-00012-of-00021.safetensorsWeights5.2 GB 9d10275984cd
model-00013-of-00021.safetensorsWeights5.2 GB 2a894851d5da
model-00014-of-00021.safetensorsWeights5.2 GB ddc7e07e1f65
model-00015-of-00021.safetensorsWeights5.2 GB 2685967ee4cf
model-00016-of-00021.safetensorsWeights5.2 GB e804c5fa0973
model-00017-of-00021.safetensorsWeights5.2 GB 36b1a9604392
model-00018-of-00021.safetensorsWeights5.2 GB 390935475275
model-00019-of-00021.safetensorsWeights5.2 GB b8d136f5780a
model-00020-of-00021.safetensorsWeights5.2 GB d5b16c8abcba
model-00021-of-00021.safetensorsWeights3.8 GB e4339a78fe23
config.jsonConfiguration183.2 KB
generation_config.jsonConfiguration202 B
model.safetensors.index.jsonConfiguration405.2 KB
oq_imatrix_report.jsonConfiguration67.1 KB
preprocessor_config.jsonConfiguration390 B
README.mdDocumentation321 B
chat_template.jinjaOther9.0 KB
.gitattributesRepository1.6 KB
merges.txtTokenizer3.4 MB
tokenizer.jsonTokenizer12.8 MB 0997f410c57a
tokenizer_config.jsonTokenizer17.9 KB
vocab.jsonTokenizer6.7 MB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
106.3 GB
Download from Robot Haus

Released by Robot Haus through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published106.3 GB
16-bit360.0 GB
8-bit180.0 GB
4-bit90.0 GB

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

Questions About Qwen3.8-Flash-Next-oQ4e-mtp

How much GPU memory does Qwen3.8-Flash-Next-oQ4e-mtp need?

About 432 GB at 16-bit and 108 GB at 4-bit: the weights (180B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run Qwen3.8-Flash-Next-oQ4e-mtp on?

At 16-bit, 2x MI325X from $4.00 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

What is Qwen3.8-Flash-Next-oQ4e-mtp's context length?

262,144 tokens, from the maximum position embeddings in its published configuration.