Bonsai 8B AWQ 4 Bit — Hardware Requirements & GPU Compatibility
Chat
Bonsai 8B AWQ 4 Bit is a 8.2B-parameter open language model from prism-ml. It supports a context window of up to 65,536 tokens. At BF16 it needs about 16.98 GB of VRAM — see which GPUs and Macs can run it below.
461 downloads
3 likesSpecifications
- Publisher
- prism-ml
- Parameters
- 8.2B
- Architecture
- Qwen3ForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 151,669
- Release Date
- 2026-05-04
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Bonsai 8B AWQ 4 Bit Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 17.0 GB | 26.3 GB | 16.38 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Bonsai 8B AWQ 4 Bit?
BF16 · 17.0 GBBonsai 8B AWQ 4 Bit (BF16) requires 17.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 23+ GB is recommended. Using the full 66K context window can add up to 9.4 GB, bringing total usage to 26.3 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Bonsai 8B AWQ 4 Bit?
BF16 · 17.0 GB21 devices with unified memory can run Bonsai 8B AWQ 4 Bit, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Bonsai 8B AWQ 4 Bit need?
Bonsai 8B AWQ 4 Bit requires 17.0 GB of VRAM at BF16. Full 66K context adds up to 9.4 GB (26.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 8.2B × 16 bits ÷ 8 = 16.4 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 9.9 GB (at full 66K context)
VRAM usage by quantization
BF1617.0 GBBF16 + full context26.3 GB- Can I run Bonsai 8B AWQ 4 Bit on a Mac?
Bonsai 8B AWQ 4 Bit requires at least 17.0 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 Bonsai 8B AWQ 4 Bit locally?
Yes — Bonsai 8B AWQ 4 Bit can run locally on consumer hardware. At BF16 quantization it needs 17.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Bonsai 8B AWQ 4 Bit?
At BF16, Bonsai 8B AWQ 4 Bit can reach ~172 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~39 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 ÷ 17.0 × 0.55 = ~172 tok/s
Estimated speed at BF16 (17.0 GB)
~172 tok/s~39 tok/s~128 tok/s~106 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Bonsai 8B AWQ 4 Bit?
At BF16, the download is about 16.38 GB.
- Which GPUs can run Bonsai 8B AWQ 4 Bit?
6 consumer GPUs can run Bonsai 8B AWQ 4 Bit at BF16 (17.0 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Bonsai 8B AWQ 4 Bit?
21 devices with unified memory can run Bonsai 8B AWQ 4 Bit at BF16 (17.0 GB), including Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.