Qwen3.8-27B-oQ4e-fp16-mtp is an open-weight model from Scott Lowry. It has 27.8B parameters and a 262,144-token context. At 16-bit it needs about 66.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 623 downloads a month.
This model was quantized using oQ (oMLX v0.7.1.dev1) mixed-precision quantization.
Runs On
What it takes to serve Qwen3.8-27B-oQ4e-fp16-mtp (27.8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 55.6 GB | 66.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 27.8 GB | 33.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 13.9 GB | 16.7 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 Oct 23, 2026.
Qwen3.8-27B-oQ4e-fp16-mtp on every accelerator the SAVRN Index prices, at every precision
Model Card
This model was quantized using oQ (oMLX v0.7.1.dev1) mixed-precision quantization.
Excerpt from the card by Scott Lowry.
Configuration
- Architecture
- Qwen3_5ForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 64
- Hidden size
- 5,120
- Feed-forward size
- 17,408
- Attention heads
- 24
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- qwen3_5
Identity and Version
- Repository
- scottlowry/Qwen3.8-27B-oQ4e-fp16-mtp
- Publisher
- Scott Lowry
- Task
- Not stated by the source
- Modality
- Other
- Library
- mlx
- Parameters
- 27.8B parameters
- Languages
- mlx, oq
- Revision
- 90dc5152413826de564ca6bf98f96dbde8a562fb
- First published
- 2026-08-14
- Last updated
- 2026-10-12
Files and Weights
16 files, 17.9 GB in total. The weights are 4 files totalling 17.9 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00004.safetensors | Weights | 5.0 GB | c06204b59ce7 |
| model-00002-of-00004.safetensors | Weights | 5.0 GB | 631d735b19fd |
| model-00003-of-00004.safetensors | Weights | 5.0 GB | 2a9113723ff9 |
| model-00004-of-00004.safetensors | Weights | 2.8 GB | d512758a5766 |
| config.json | Configuration | 47.3 KB | — |
| generation_config.json | Configuration | 202 B | — |
| model.safetensors.index.json | Configuration | 212.2 KB | — |
| oq_imatrix_report.json | Configuration | 31.2 KB | — |
| preprocessor_config.json | Configuration | 390 B | — |
| README.md | Documentation | 512 B | — |
| chat_template.jinja | Other | 9.0 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 3.4 MB | — |
| tokenizer.json | Tokenizer | 12.8 MB | 0997f410c57a |
| tokenizer_config.json | Tokenizer | 17.9 KB | — |
| vocab.json | Tokenizer | 6.7 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 17.9 GB
Released by Scott Lowry through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 17.9 GB |
| 16-bit | 55.6 GB |
| 8-bit | 27.8 GB |
| 4-bit | 13.9 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwen3.8-27B-oQ4e-fp16-mtp
How much GPU memory does Qwen3.8-27B-oQ4e-fp16-mtp need?
About 66.7 GB at 16-bit and 16.7 GB at 4-bit: the weights (27.8B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Qwen3.8-27B-oQ4e-fp16-mtp 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 Qwen3.8-27B-oQ4e-fp16-mtp's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.