Bonsai 1.7B Unpacked — Hardware Requirements & GPU Compatibility
ChatFunctions
Bonsai 1.7B Unpacked is a 1.7B-parameter open language model from prism-ml. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 1.57 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 · 32K)Best on 24 GB (Q4_K_M · ~417 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~46 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Bonsai 1.7B Unpacked
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/prism-ml/Bonsai-1.7B-ggufQ4_K_M fits fully on the RTX 4090 · 20.8 GB free · 16K context
Download: Bonsai-1.7B-Q4_K_M.gguf1.03 GBprism-ml
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (8 GB headroom) · Q4_K_M
- Generation speed
- ~149 tok/s
- generation speed
- Cost per 1M output tokens
- $0.13
- per 1M output tokens
How Much VRAM Does Bonsai 1.7B Unpacked Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.3 GB | 4.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~516 tok/s | |
| 1.4 GB | 4.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~478 tok/s | |
| 1.6 GB | 5.1 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~417 tok/s | |
| 1.8 GB | 5.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~372 tok/s | |
| 1.9 GB | 5.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~336 tok/s | |
| 2.3 GB | 5.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~291 tok/s | |
| 4.0 GB | 7.5 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~165 tok/s |
Selected Q4_K_M
4-bit medium quantization3.2GBat 16K context
- Weights
- 1.0 GB
- KV cache
- 1.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.8 GB free · ~417 tok/s
≥50 tok/s needs ≥121 GB/s · RTX 5090 ~742, RTX 3090 Ti ~417
Which Hardware Can Run Bonsai 1.7B Unpacked?
Q4_K_M · 1.6 GBBonsai 1.7B Unpacked (Q4_K_M) requires 1.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 33K context window can add up to 3.5 GB, bringing total usage to 5.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Bonsai 1.7B Unpacked, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.8 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~315Simulate output on RTX 3080RTX 2080 Ti~255Simulate output on RTX 2080 TiRTX 3070 Ti~252Simulate output on RTX 3070 TiM3*8 GB~46Simulate output on iMac 24" M3 (8 GB)Orin Nano~42Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~30Simulate output on iPhone 1720 GB
fits · 16.8 GB free · up to 32K ctx
1 GPU
RX 7900 XT~306Simulate output on RX 7900 XT32–40 GB
fits · 28.8 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~742Simulate output on RTX 5090M5 Max36 GB~205Simulate output on Mac Studio M5 Max (36 GB)M532 GB~69Simulate output on MacBook Air 13" M5 (32 GB)Orin~85Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~56Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
5| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Granite 4.0 1BIBM | — | 2.6 GB | ~452 | same size |
| Qwen 1 8BAlibaba | — | 1.9 GB | ~542 | same size |
| Qwen3 1.7B BaseAlibaba | — | 3.2 GB | ~417 | same size |
| DeepSeek R1 Distill Qwen 1.5BDeepSeek | — | 1.8 GB | ~461 | same size |
| SmolLM2 1.7B InstructHugging Face | — | 2.9 GB | ~379 | same size |
Specifications
- Publisher
- prism-ml
- Parameters
- 1.7B
- Architecture
- Qwen3ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 151,669
- Release Date
- 2026-03-29
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Bonsai 1.7B Unpacked need?
Bonsai 1.7B Unpacked requires 1.6 GB of VRAM at Q4_K_M, or 4.0 GB at BF16. Full 33K context adds up to 3.5 GB (5.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.7B × 4.8 bits ÷ 8 = 1 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 ≈ 4.1 GB (at full 33K context)
VRAM usage by quantization
What's the best quantization for Bonsai 1.7B Unpacked?
For Bonsai 1.7B Unpacked, Q4_K_M (1.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Bonsai 1.7B Unpacked on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Bonsai 1.7B Unpacked. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Bonsai 1.7B Unpacked locally?
Yes — Bonsai 1.7B Unpacked can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Bonsai 1.7B Unpacked?
At Q4_K_M, Bonsai 1.7B Unpacked can reach ~3057 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~417 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 ÷ 1.57 × 0.65 = ~3312 tok/s
Estimated speed at Q4_K_M (1.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Bonsai 1.7B Unpacked?
At Q4_K_M, the download is about 1.03 GB. The full-precision BF16 version is 3.44 GB. The smallest option (Q2_K) is 0.73 GB.
Which GPUs can run Bonsai 1.7B Unpacked?
52 consumer GPUs can run Bonsai 1.7B Unpacked 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 Bonsai 1.7B Unpacked?
163 devices with unified memory can run Bonsai 1.7B Unpacked at Q4_K_M (1.6 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.