StorySupra 10M — Hardware Requirements & GPU Compatibility
Chat
StorySupra 10M is a 13M-parameter open language model from SupraLabs. It supports a context window of up to 256 tokens. At BF16 it needs about 0.34 GB of VRAM — see which GPUs and Macs can run it below.
196 downloads
6 likesSpecifications
- Publisher
- SupraLabs
- Parameters
- 13M
- Architecture
- LlamaForCausalLM
- Context Length
- 256 tokens
- Vocabulary Size
- 8,192
- Release Date
- 2026-05-15
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does StorySupra 10M Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 0.3 GB | — | 0.03 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run StorySupra 10M?
BF16 · 0.3 GBStorySupra 10M (BF16) requires 0.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run StorySupra 10M?
BF16 · 0.3 GB33 devices with unified memory can run StorySupra 10M, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does StorySupra 10M need?
StorySupra 10M requires 0.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 13M × 16 bits ÷ 8 = 0 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF160.3 GB- Can I run StorySupra 10M on a Mac?
StorySupra 10M requires at least 0.3 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run StorySupra 10M locally?
Yes — StorySupra 10M can run locally on consumer hardware. At BF16 quantization it needs 0.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is StorySupra 10M?
At BF16, StorySupra 10M can reach ~8574 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~1927 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 0.3 × 0.55 = ~8574 tok/s
Estimated speed at BF16 (0.3 GB)
~8574 tok/s~1927 tok/s~6408 tok/s~5301 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of StorySupra 10M?
At BF16, the download is about 0.03 GB.
- Which GPUs can run StorySupra 10M?
35 consumer GPUs can run StorySupra 10M at BF16 (0.3 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run StorySupra 10M?
33 devices with unified memory can run StorySupra 10M at BF16 (0.3 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.