Qwen3.5-4B-oQ4e-mtp is an open-weight model from Bambocher. It has 4.7B parameters and a 262,144-token context. At 16-bit it needs about 11.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 14 downloads a month.
This model was quantized using oQ (oMLX v0.7.1rc1) mixed-precision quantization. The effective average is 5.606 bits/weight for the complete checkpoint.
Runs On
What it takes to serve Qwen3.5-4B-oQ4e-mtp (4.7B 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 | 9.3 GB | 11.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.7 GB | 5.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.3 GB | 2.8 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.
Qwen3.5-4B-oQ4e-mtp on every accelerator the SAVRN Index prices, at every precision
Model Card
This model was quantized using oQ (oMLX v0.7.1rc1) mixed-precision quantization. The effective average is 5.606 bits/weight for the complete checkpoint.
Excerpt from the card by Bambocher.
Configuration
- Architecture
- Qwen3_5ForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 32
- Hidden size
- 2,560
- Feed-forward size
- 9,216
- Attention heads
- 16
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- qwen3_5
Identity and Version
- Repository
- bambocher/Qwen3.5-4B-oQ4e-mtp
- Publisher
- Bambocher
- Task
- Not stated by the source
- Modality
- Other
- Library
- mlx
- Parameters
- 4.7B parameters
- Languages
- mlx, oq, mtp
- Revision
- d608c3c539547bbeba850f2a99955731b123fcb9
- First published
- 2026-08-17
- Last updated
- 2026-10-20
Files and Weights
11 files, 3.3 GB in total. The weights are 1 file totalling 3.3 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.3 GB | 16e14d657b93 |
| config.json | Configuration | 26.8 KB | — |
| oq_imatrix_report.json | Configuration | 17.3 KB | — |
| preprocessor_config.json | Configuration | 390 B | — |
| README.md | Documentation | 1.1 KB | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 3.4 MB | — |
| tokenizer.json | Tokenizer | 12.8 MB | 5f9e4d4901a9 |
| tokenizer_config.json | Tokenizer | 16.7 KB | — |
| vocab.json | Tokenizer | 6.7 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 3.3 GB
Released by Bambocher through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.3 GB |
| 16-bit | 9.3 GB |
| 8-bit | 4.7 GB |
| 4-bit | 2.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwen3.5-4B-oQ4e-mtp
How much GPU memory does Qwen3.5-4B-oQ4e-mtp need?
About 11.2 GB at 16-bit and 2.8 GB at 4-bit: the weights (4.7B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Qwen3.5-4B-oQ4e-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 Qwen3.5-4B-oQ4e-mtp's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.