Stories15M MOE — Hardware Requirements & GPU Compatibility
Chat
Stories15M MOE is a 36M-parameter open language model from ggml-org. It supports a context window of up to 256 tokens. At Q4_K_M it needs about 0.34 GB of VRAM — see which GPUs and Macs can run it below.
88.1K downloads
8 likesSpecifications
- Publisher
- ggml-org
- Parameters
- 36M
- Architecture
- MixtralForCausalLM
- Context Length
- 256 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-07-11
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Stories15M MOE Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 0.3 GB | — | 0.02 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 0.3 GB | — | 0.02 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 0.3 GB | — | 0.02 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 0.3 GB | — | 0.03 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 0.3 GB | — | 0.03 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 0.3 GB | — | 0.04 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 0.4 GB | — | 0.07 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Stories15M MOE?
Q4_K_M · 0.3 GBStories15M MOE (Q4_K_M) 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. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Stories15M MOE?
Q4_K_M · 0.3 GB59 devices with unified memory can run Stories15M MOE, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomFrequently Asked Questions
- How much VRAM does Stories15M MOE need?
Stories15M MOE requires 0.3 GB of VRAM at Q4_K_M, or 0.4 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 36M × 4.8 bits ÷ 8 = 0 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M0.3 GB- What's the best quantization for Stories15M MOE?
For Stories15M MOE, Q4_K_M (0.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.3 GB.
VRAM requirement by quantization
Q2_K0.3 GBQ4_K_M ★0.3 GBQ5_K_M0.3 GBQ6_K0.3 GBQ8_00.3 GBBF160.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Stories15M MOE on a Mac?
Stories15M MOE requires at least 0.3 GB at Q2_K, 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 Stories15M MOE locally?
Yes — Stories15M MOE can run locally on consumer hardware. At Q4_K_M quantization it needs 0.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Stories15M MOE?
At Q4_K_M, Stories15M MOE can reach ~797 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1360 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 0.3 × 0.65 = ~2624 tok/s
Estimated speed at Q4_K_M (0.3 GB)
~2624 tok/s~1360 tok/s~2624 tok/s~2419 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Stories15M MOE?
At Q4_K_M, the download is about 0.02 GB. The full-precision BF16 version is 0.07 GB. The smallest option (Q2_K) is 0.02 GB.
- Which GPUs can run Stories15M MOE?
52 consumer GPUs can run Stories15M MOE at Q4_K_M (0.3 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Stories15M MOE?
59 devices with unified memory can run Stories15M MOE at Q4_K_M (0.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.