NVFP4 variant of Qwen 3.6 35B for reasoning and tool calling.
Parameters35.1B
Context—
Weights—
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve occamy-1.0-mlx-4bit (35.1B 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 | 70.2 GB | 84.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x MI325X $2.00 · 1x MI355X $2.59 |
| 8-bit | 35.1 GB | 42.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 17.6 GB | 21.1 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
Identity and Version
- Repository
- tozp/occamy-1.0-mlx-4bit
- Publisher
- Ray
- Task
- Image and text to text
- Modality
- Image and text
- Library
- transformers
- Parameters
- 35.1B parameters
- Languages
- co-work
- Revision
- 1737d534e09c605637649ff75d11dd900ab75e07
- First published
- 2026-09-18
- Last updated
- 2026-09-18
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
Download from Ray
Released by Ray through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3.6-35B-A3B
- Described by arXiv:2609.11977
- Quantized from Qwen/Qwen3.6-35B-A3B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 70.2 GB |
| 8-bit | 35.1 GB |
| 4-bit | 17.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About occamy-1.0-mlx-4bit
How much GPU memory does occamy-1.0-mlx-4bit need?
About 84.3 GB at 16-bit and 21.1 GB at 4-bit: the weights (35.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run occamy-1.0-mlx-4bit 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.
Can I use occamy-1.0-mlx-4bit commercially?
Yes. occamy-1.0-mlx-4bit is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. This release delivers substantial upgrades, particularly in For more details, please refer to our blog post Qwen3.6-35B-A3B. Empty cells (--) indicate scores not available or not applicable. For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API. Qwen3.6 can be served via APIs with popular inference frameworks. In…
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL. Empty cells (--) indicate scores not yet available or not applicable. Empty cells (--) indicate scores not…
Base: Qwen/Qwen3.6-35B-A3B-FP8 (same FP8 block format/scales convention). Adapter: qwen3.6-35b-a3b-tool-prompts-ckpt444-adapter (LoRA r=32, 2 epochs, 1873 dialogues). Merged in BF16 (RAM only), block-requantized to FP8 e4m3/128. Chat template: qwen3template333.jinja. Serve with sglang / vllm / transformers.
Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. This release delivers substantial upgrades, particularly in For more details, please refer to our blog post Qwen3.6-35B-A3B. Empty cells (--) indicate scores not available or not applicable. For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API. Qwen3.6 can be served via APIs with popular inference frameworks. In…
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. For more details, please refer to our blog post Qwen3.5. WMT24++: a harder subset of WMT24 after difficulty labeling and rebalancing; we report the averaged scores on 55 languages using XCOMET-XXL. Empty cells (--) indicate scores not yet available or not applicable. Empty cells (--) indicate scores not…