Ternary Bonsai 2 27B Vllm — Hardware Requirements & GPU Compatibility
Chat
Ternary Bonsai 2 27B Vllm is a 3.5B-parameter open language model from fraserprice. It supports a context window of up to 262,144 tokens. At BF16 it needs about 7.79 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 8K)Best on 24 GB (BF16 · ~84 tok/s · 256K)Macs from 16 GB (BF16 · ~18 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Ternary Bonsai 2 27B Vllm
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 fraserprice/Ternary-Bonsai-2-27B-vllm --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 RTX 3080 Ti (12 GB) (3 GB headroom) · BF16
- Generation speed
- ~76 tok/s
- generation speed
- Cost per 1M output tokens
- $0.45
- per 1M output tokens
How Much VRAM Does Ternary Bonsai 2 27B Vllm Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 7.8 GB | 9.1 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 256K context · ~84 tok/s |
Selected BF16
Brain floating point 168.2GBat 16K context
- Weights
- 7.0 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 15.8 GB free · ~84 tok/s
≥50 tok/s needs ≥599 GB/s · RTX 5090 ~150, RTX 3090 Ti ~84
Which Hardware Can Run Ternary Bonsai 2 27B Vllm?
BF16 · 7.8 GBTernary Bonsai 2 27B Vllm (BF16) requires 7.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 11+ GB is recommended. Using the full 262K context window can add up to 13.9 GB, bringing total usage to 21.7 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080. 151 devices with unified memory can run Ternary Bonsai 2 27B Vllm, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
12 GB
12 GB tier →fits · 3.8 GB free · up to 64K ctx
10 GPUs
RTX 3080 Ti~76Simulate output on RTX 3080 TiRTX 5070~56Simulate output on RTX 5070RTX 4070~42Simulate output on RTX 407020 GB
fits · 11.8 GB free · up to 128K ctx
1 GPU
RX 7900 XT~62Simulate output on RX 7900 XT32–40 GB
fits · 23.8 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~150Simulate output on RTX 5090M5 Max36 GB~41Simulate output on Mac Studio M5 Max (36 GB)M532 GB~14Simulate output on MacBook Air 13" M5 (32 GB)Orin~17Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~11Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite 4.0 MicroIBM | — | 3.7 GB | ~261 | same size |
| Qwen2.5 VL 3B InstructAlibaba | — | 3.2 GB | ~249 | same size |
| Deepseek Vl2 TinyDeepSeek | — | 9.4 GB | ~152 | same size |
| Tiny Aya GlobalCohere | — | 9.4 GB | ~89 | same size |
| Phi Tiny MoE InstructMicrosoft | — | 3.1 GB | ~309 | same size |
| MiniMax M3 EAGLE3Inferact | — | 2.7 GB | ~284 | same size |
Specifications
- Publisher
- fraserprice
- Parameters
- 3.5B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-09-18
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Ternary Bonsai 2 27B Vllm need?
Ternary Bonsai 2 27B Vllm requires 7.8 GB of VRAM at BF16. Full 262K context adds up to 13.9 GB (21.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.5B × 16 bits ÷ 8 = 7 GB
KV Cache + Overhead ≈ 0.8 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 ≈ 14.7 GB (at full 262K context)
VRAM usage by quantization
Can I run Ternary Bonsai 2 27B Vllm on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Ternary Bonsai 2 27B Vllm. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 7.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Ternary Bonsai 2 27B Vllm locally?
Yes — Ternary Bonsai 2 27B Vllm can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Ternary Bonsai 2 27B Vllm?
At BF16, Ternary Bonsai 2 27B Vllm can reach ~616 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~84 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 ÷ 7.79 × 0.65 = ~668 tok/s
Estimated speed at BF16 (7.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Ternary Bonsai 2 27B Vllm?
At BF16, the download is about 7.04 GB.
Which GPUs can run Ternary Bonsai 2 27B Vllm?
52 consumer GPUs can run Ternary Bonsai 2 27B Vllm at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 36 GPUs have plenty of headroom for comfortable inference.
Which devices can run Ternary Bonsai 2 27B Vllm?
151 devices with unified memory can run Ternary Bonsai 2 27B Vllm at BF16 (7.8 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.