QU SSM 130M MoE — Hardware Requirements & GPU Compatibility
Chat
QU SSM 130M MoE is a 135M-parameter open language model from Prannesshkva. At BF16 it needs about 0.30 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 32K)Best on 24 GB (BF16 · ~2184 tok/s · 32K)Macs from 8 GB (BF16 · ~239 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run QU SSM 130M MoE
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve Prannesshkva/QU-SSM-130M-MoE --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (10 GB headroom) · BF16
- Generation speed
- ~780 tok/s
- generation speed
- Cost per 1M output tokens
- $0.030
- per 1M output tokens
How Much VRAM Does QU SSM 130M MoE Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.3 GB | 2.1 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~2184 tok/s |
Selected BF16
Brain floating point 161.1GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.9 GB free · ~2184 tok/s
≥50 tok/s needs ≥23 GB/s · RTX 5090 ~3883, RTX 3090 Ti ~2184
Which Hardware Can Run QU SSM 130M MoE?
BF16 · 0.3 GBQU SSM 130M MoE (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. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run QU SSM 130M MoE, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.9 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~1647Simulate output on RTX 3080RTX 2080 Ti~1335Simulate output on RTX 2080 TiRTX 3070 Ti~1318Simulate output on RTX 3070 TiM3*8 GB~239Simulate output on iMac 24" M3 (8 GB)Orin Nano~221Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~159Simulate output on iPhone 1720 GB
fits · 18.9 GB free · up to 32K ctx
1 GPU
RX 7900 XT~1600Simulate output on RX 7900 XT32–40 GB
fits · 30.9 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~3883Simulate output on RTX 5090M5 Max36 GB~1073Simulate output on Mac Studio M5 Max (36 GB)M532 GB~358Simulate output on MacBook Air 13" M5 (32 GB)Orin~444Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~293Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| SmolLM 135M Instruct FP32modularai | — | 0.4 GB | ~1524 | same size |
Specifications
- Publisher
- Prannesshkva
- Parameters
- 135M
- Architecture
- QUSSMForCausalLM
- Vocabulary Size
- 50,257
- Release Date
- 2026-08-31
- License
- Other
Frequently Asked Questions
How much VRAM does QU SSM 130M MoE need?
QU SSM 130M MoE requires 0.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 135M × 16 bits ÷ 8 = 0.3 GB
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can I run QU SSM 130M MoE on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run QU SSM 130M MoE. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run QU SSM 130M MoE locally?
Yes — QU SSM 130M MoE can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is QU SSM 130M MoE?
At BF16, QU SSM 130M MoE can reach ~16000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~2184 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 = ~17333 tok/s
Estimated speed at BF16 (0.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of QU SSM 130M MoE?
At BF16, the download is about 0.27 GB.
Which GPUs can run QU SSM 130M MoE?
52 consumer GPUs can run QU SSM 130M MoE at BF16. 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 QU SSM 130M MoE?
163 devices with unified memory can run QU SSM 130M MoE at BF16 (0.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.