BAAR2 150M — Hardware Requirements & GPU Compatibility
Chat
BAAR2 150M is a 168M-parameter open language model from aixk. It supports a context window of up to 512 tokens. At FP16 it needs about 0.37 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (FP16)Best on 24 GB (FP16 · ~1771 tok/s)Macs from 8 GB (FP16 · ~194 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run BAAR2 150M
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 aixk/BAAR2-150M --max-model-len 512vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (11 GB headroom) · FP16
- Generation speed
- ~1603 tok/s
- generation speed
- Cost per 1M output tokens
- $0.021
- per 1M output tokens
How Much VRAM Does BAAR2 150M Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.4 GB | — | 16-bit · full — Full half-precision — baseline for inference | Fits: — context · ~1771 tok/s |
Selected FP16
Full half-precision0.4GBat 1K context
- Weights
- 0.1 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.6 GB free · ~1771 tok/s
≥50 tok/s needs ≥28 GB/s · RTX 5090 ~3148, RTX 3090 Ti ~1771
Which Hardware Can Run BAAR2 150M?
FP16 · 0.4 GBBAAR2 150M (FP16) requires 0.4 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 BAAR2 150M, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.6 GB free · up to — ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~1336Simulate output on RTX 3080RTX 2080 Ti~1082Simulate output on RTX 2080 TiRTX 3070 Ti~1069Simulate output on RTX 3070 TiM3*8 GB~194Simulate output on iMac 24" M3 (8 GB)Orin Nano~179Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~129Simulate output on iPhone 1720 GB
fits · 19.6 GB free · up to — ctx
1 GPU
RX 7900 XT~1297Simulate output on RX 7900 XT32–40 GB
fits · 31.6 GB free · up to — ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~3148Simulate output on RTX 5090M5 Max36 GB~870Simulate output on Mac Studio M5 Max (36 GB)M532 GB~291Simulate output on MacBook Air 13" M5 (32 GB)Orin~360Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~237Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at FP16
Similar models
1| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llama 160MJackFram | — | 0.5 GB | ~1394 | same size |
Specifications
- Publisher
- aixk
- Parameters
- 168M
- Architecture
- FHN_T4Max_150M
- Context Length
- 512 tokens
- Vocabulary Size
- 10,240
- Release Date
- 2026-09-12
- License
- Other
Frequently Asked Questions
How much VRAM does BAAR2 150M need?
BAAR2 150M requires 0.4 GB of VRAM at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 168M × 16 bits ÷ 8 = 0.3 GB
KV Cache + Overhead ≈ 0.1 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.
VRAM usage by quantization
Can I run BAAR2 150M on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run BAAR2 150M. Apple Silicon uses unified memory, so the model shares RAM with the system. At FP16 you need at least 0.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run BAAR2 150M locally?
Yes — BAAR2 150M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is BAAR2 150M?
At FP16, BAAR2 150M can reach ~12973 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1771 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 ÷ 0.37 × 0.65 = ~14054 tok/s
Estimated speed at FP16 (0.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of BAAR2 150M?
At FP16, the download is about 0.34 GB.
Which GPUs can run BAAR2 150M?
52 consumer GPUs can run BAAR2 150M at FP16. 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 BAAR2 150M?
163 devices with unified memory can run BAAR2 150M at FP16 (0.4 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.