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.
1.1K downloads
4 likesSpecifications
- 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
Get Started
HuggingFace
How Much VRAM Does Ternary Bonsai 2 27B Vllm Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 7.8 GB | 64.6 GB | 7.04 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs 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 56.8 GB, bringing total usage to 64.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Ternary Bonsai 2 27B Vllm?
BF16 · 7.8 GB55 devices with unified memory can run Ternary Bonsai 2 27B Vllm, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 GB).
Runs great
— Plenty of headroomRelated Models
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 56.8 GB (64.6 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)
KV Cache + Overhead ≈ 57.6 GB (at full 262K context)
VRAM usage by quantization
BF167.8 GBBF16 + full context64.6 GB- Can I run Ternary Bonsai 2 27B Vllm on a Mac?
Ternary Bonsai 2 27B Vllm requires at least 7.8 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Ternary Bonsai 2 27B Vllm locally?
Yes — Ternary Bonsai 2 27B Vllm can run locally on consumer hardware. At BF16 quantization it needs 7.8 GB of VRAM. 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 ÷ 7.8 × 0.65 = ~668 tok/s
Estimated speed at BF16 (7.8 GB)
~668 tok/s~84 tok/s~668 tok/s~616 tok/sReal-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 (7.8 GB). 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?
59 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, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.