S1 Mini — Hardware Requirements & GPU Compatibility
ChatFunctions
S1 Mini is a 752M-parameter open language model from superwhisper. It supports a context window of up to 40,960 tokens. At Q4_K_M it needs about 0.87 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 40K)Best on 24 GB (Q4_K_M · ~753 tok/s · 40K)Macs from 8 GB (Q4_K_M · ~82 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run S1 Mini
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/superwhisper/s1-mini-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 22.3 GB free · 16K context
Download: s1-mini-q4_k_m.gguf0.48 GBsuperwhisper
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (10 GB headroom) · Q4_K_M
- Generation speed
- ~269 tok/s
- generation speed
- Cost per 1M output tokens
- $0.086
- per 1M output tokens
How Much VRAM Does S1 Mini Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.7 GB | 2.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 40K context · ~885 tok/s | |
| 0.8 GB | 2.5 GB | 3-bit medium — 3-bit medium quantization | Fits: 40K context · ~840 tok/s | |
| 0.9 GB | 2.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 40K context · ~753 tok/s | |
| 0.9 GB | 2.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 40K context · ~690 tok/s | |
| 1.0 GB | 2.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 40K context · ~630 tok/s | |
| 1.2 GB | 2.9 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 40K context · ~560 tok/s | |
| 1.9 GB | 3.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 40K context · ~341 tok/s |
Selected Q4_K_M
4-bit medium quantization1.7GBat 16K context
- Weights
- 0.5 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.3 GB free · ~753 tok/s
≥50 tok/s needs ≥67 GB/s · RTX 5090 ~1339, RTX 3090 Ti ~753
Which Hardware Can Run S1 Mini?
Q4_K_M · 0.9 GBS1 Mini (Q4_K_M) requires 0.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 41K context window can add up to 2.2 GB, bringing total usage to 3.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run S1 Mini, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.3 GB free · up to 40K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~568Simulate output on RTX 3080RTX 2080 Ti~460Simulate output on RTX 2080 TiRTX 3070 Ti~455Simulate output on RTX 3070 TiM3*8 GB~82Simulate output on iMac 24" M3 (8 GB)Orin Nano~76Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~55Simulate output on iPhone 1720 GB
fits · 18.3 GB free · up to 40K ctx
1 GPU
RX 7900 XT~552Simulate output on RX 7900 XT32–40 GB
fits · 30.3 GB free · up to 40K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1339Simulate output on RTX 5090M5 Max36 GB~370Simulate output on Mac Studio M5 Max (36 GB)M532 GB~124Simulate output on MacBook Air 13" M5 (32 GB)Orin~153Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~101Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3 0.6BAlibaba | — | 1.7 GB | ~753 | same size |
Specifications
- Publisher
- superwhisper
- Parameters
- 752M
- Architecture
- Qwen3ForCausalLM
- Context Length
- 40,960 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-08-12
- License
- Other
Frequently Asked Questions
How much VRAM does S1 Mini need?
S1 Mini requires 0.9 GB of VRAM at Q4_K_M, or 1.9 GB at BF16. Full 41K context adds up to 2.2 GB (3.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 752M × 4.8 bits ÷ 8 = 0.5 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 2.6 GB (at full 41K context)
VRAM usage by quantization
What's the best quantization for S1 Mini?
For S1 Mini, Q4_K_M (0.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (0.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run S1 Mini on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run S1 Mini. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run S1 Mini locally?
Yes — S1 Mini can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is S1 Mini?
At Q4_K_M, S1 Mini can reach ~5517 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~753 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 ÷ 0.87 × 0.65 = ~5977 tok/s
Estimated speed at Q4_K_M (0.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of S1 Mini?
At Q4_K_M, the download is about 0.45 GB. The full-precision BF16 version is 1.50 GB. The smallest option (Q2_K) is 0.32 GB.
Which GPUs can run S1 Mini?
52 consumer GPUs can run S1 Mini at Q4_K_M. 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 S1 Mini?
163 devices with unified memory can run S1 Mini at Q4_K_M (0.9 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.