Ternary Bonsai 8B Unpacked — Hardware Requirements & GPU Compatibility
Chat
Ternary Bonsai 8B Unpacked is a 8.2B-parameter open language model from prism-ml. It supports a context window of up to 65,536 tokens. At Q4_K_M it needs about 5.52 GB of VRAM — see which GPUs and Macs can run it below.
226.6K downloads
12 likesSpecifications
- Publisher
- prism-ml
- Parameters
- 8.2B
- Architecture
- Qwen3ForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 151,669
- Release Date
- 2026-04-13
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Ternary Bonsai 8B Unpacked Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 4.1 GB | 13.4 GB | 3.48 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 4.6 GB | 14.0 GB | 3.99 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 5.5 GB | 14.9 GB | 4.91 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 6.4 GB | 15.8 GB | 5.83 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 7.4 GB | 16.7 GB | 6.76 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 8.8 GB | 18.1 GB | 8.19 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 17.0 GB | 26.3 GB | 16.38 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 8B Unpacked?
Q4_K_M · 5.5 GBTernary Bonsai 8B Unpacked (Q4_K_M) requires 5.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 66K context window can add up to 9.4 GB, bringing total usage to 14.9 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Ternary Bonsai 8B Unpacked?
Q4_K_M · 5.5 GB33 devices with unified memory can run Ternary Bonsai 8B Unpacked, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Ternary Bonsai 8B Unpacked
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Ternary Bonsai 8B Unpacked need?
Ternary Bonsai 8B Unpacked requires 5.5 GB of VRAM at Q4_K_M, or 17.0 GB at BF16. Full 66K context adds up to 9.4 GB (14.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.2B × 4.8 bits ÷ 8 = 4.9 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 10 GB (at full 66K context)
VRAM usage by quantization
Q4_K_M5.5 GBQ4_K_M + full context14.9 GB- What's the best quantization for Ternary Bonsai 8B Unpacked?
For Ternary Bonsai 8B Unpacked, Q4_K_M (5.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (6.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.1 GB.
VRAM requirement by quantization
Q2_K4.1 GBQ4_K_M ★5.5 GBQ5_K_M6.4 GBQ6_K7.4 GBQ8_08.8 GBBF1617.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Ternary Bonsai 8B Unpacked on a Mac?
Ternary Bonsai 8B Unpacked requires at least 4.1 GB at Q2_K, 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 8B Unpacked locally?
Yes — Ternary Bonsai 8B Unpacked can run locally on consumer hardware. At Q4_K_M quantization it needs 5.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Ternary Bonsai 8B Unpacked?
At Q4_K_M, Ternary Bonsai 8B Unpacked can reach ~528 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~119 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 5.5 × 0.55 = ~528 tok/s
Estimated speed at Q4_K_M (5.5 GB)
~528 tok/s~119 tok/s~395 tok/s~327 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 8B Unpacked?
At Q4_K_M, the download is about 4.91 GB. The full-precision BF16 version is 16.38 GB. The smallest option (Q2_K) is 3.48 GB.
- Which GPUs can run Ternary Bonsai 8B Unpacked?
35 consumer GPUs can run Ternary Bonsai 8B Unpacked at Q4_K_M (5.5 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 28 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Ternary Bonsai 8B Unpacked?
33 devices with unified memory can run Ternary Bonsai 8B Unpacked at Q4_K_M (5.5 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.