Osaurus AppleScript 16B A4B JANG 4M — Hardware Requirements & GPU Compatibility
ChatFunctions
Osaurus AppleScript 16B A4B JANG 4M is a 16.1B-parameter open language model from OsaurusAI. It supports a context window of up to 262,144 tokens. At BF16 it needs about 32.90 GB of VRAM — see which GPUs and Macs can run it below.
Osaurus AppleScript 16B A4B JANG 4M runs on a 48 GB+ Mac or a workstation GPU
Best local pick → Mac Studio M5 Max (48 GB) · BF16 · 33.3 GB · ~40 tok/s
Macs from 48 GB (BF16 · ~40 tok/s)
Gemma Terms
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Osaurus AppleScript 16B A4B JANG 4M
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve OsaurusAI/Osaurus-AppleScript-16B-A4B-JANG_4M --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on A100 40GB (6 GB headroom) · BF16
- Generation speed
- ~103 tok/s
- generation speed
- Cost per 1M output tokens
- $1.09
- per 1M output tokens
How Much VRAM Does Osaurus AppleScript 16B A4B JANG 4M Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 32.9 GB | 33.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 33.3 GB |
Selected BF16
Brain floating point 1633.3GBat 16K context
- Weights
- 32.3 GB
- KV cache
- 0.7 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 9.2 GB more
Or .
Which Hardware Can Run Osaurus AppleScript 16B A4B JANG 4M?
BF16 · 32.9 GBOsaurus AppleScript 16B A4B JANG 4M (BF16) requires 32.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 43+ GB is recommended. Using the full 262K context window can add up to 8.6 GB, bringing total usage to 41.5 GB. No consumer GPU has enough memory. 67 devices with unified memory can run Osaurus AppleScript 16B A4B JANG 4M, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Max (48 GB).
48 GB
48 GB tier →fits · 14.8 GB free · up to 256K ctx
2 Mac classes · 1 device family
M5 Max48 GB~40Simulate output on Mac Studio M5 Max (48 GB)M5 Pro48 GB~23Simulate output on Mac Mini M5 Pro (48 GB)Snapdragon X2 Elite Extreme (X2E-96-100)~17Simulate output on Snapdragon X2 Elite Extreme Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
4| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Kimi VL A3B InstructMoonshot AI | — | 10.7 GB | ~208 | same size |
| Moonlight 16B A3BMoonshot AI | — | 10.1 GB | ~229 | same size |
| DeepSeek v2 LiteDeepSeek | — | 10.2 GB | ~243 | same size |
| Deepseek Moe 16B ChatDeepSeek | — | 11.1 GB | ~231 | same size |
Specifications
- Publisher
- OsaurusAI
- Parameters
- 16.1B
- Active parameters
- 4B per token
- Architecture
- Gemma4ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 262,144
- Release Date
- 2026-06-21
- License
- Gemma Terms
Frequently Asked Questions
How much VRAM does Osaurus AppleScript 16B A4B JANG 4M need?
Osaurus AppleScript 16B A4B JANG 4M requires 32.9 GB of VRAM at BF16. Full 262K context adds up to 8.6 GB (41.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 16.1B × 16 bits ÷ 8 = 32.3 GB
KV Cache + Overhead ≈ 0.6 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 ≈ 9.3 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Osaurus AppleScript 16B A4B JANG 4M?
No — Osaurus AppleScript 16B A4B JANG 4M requires at least 32.9 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Osaurus AppleScript 16B A4B JANG 4M on a Mac?
Yes — Mac Studio M5 Max (48 GB) and 55 other Macs can run Osaurus AppleScript 16B A4B JANG 4M. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 32.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Osaurus AppleScript 16B A4B JANG 4M locally?
Yes — Osaurus AppleScript 16B A4B JANG 4M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Osaurus AppleScript 16B A4B JANG 4M?
At BF16, Osaurus AppleScript 16B A4B JANG 4M can reach ~130 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 8.2 GB active ÷ (8000 × 0.65) = 1.57 ms, plus 30 layers × 0.055 ms = 1.65 ms, so 1000 ÷ 3.22 ms = ~311 tok/s
Estimated speed at BF16 (32.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Osaurus AppleScript 16B A4B JANG 4M?
At BF16, the download is about 32.26 GB.
Which GPUs can run Osaurus AppleScript 16B A4B JANG 4M?
No single consumer GPU has enough VRAM to run Osaurus AppleScript 16B A4B JANG 4M at BF16 (32.9 GB). Multi-GPU or professional hardware is required.
Which devices can run Osaurus AppleScript 16B A4B JANG 4M?
67 devices with unified memory can run Osaurus AppleScript 16B A4B JANG 4M at BF16 (32.9 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (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.