Prism 1 Mini — Hardware Requirements & GPU Compatibility
Chat
Prism 1 Mini is a 752M-parameter open language model from TreeSoft. It supports a context window of up to 262,144 tokens. At BF16 it needs about 1.86 GB of VRAM — see which GPUs and Macs can run it below.
2 likesSpecifications
- Publisher
- TreeSoft
- Parameters
- 752M
- Architecture
- Qwen3_5ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-07-19
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Prism 1 Mini Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 1.9 GB | 8.3 GB | 1.50 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 Prism 1 Mini?
BF16 · 1.9 GBPrism 1 Mini (BF16) requires 1.9 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 262K context window can add up to 6.4 GB, bringing total usage to 8.3 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Prism 1 Mini?
BF16 · 1.9 GB59 devices with unified memory can run Prism 1 Mini, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Prism 1 Mini need?
Prism 1 Mini requires 1.9 GB of VRAM at BF16. Full 262K context adds up to 6.4 GB (8.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 752M × 16 bits ÷ 8 = 1.5 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 6.8 GB (at full 262K context)
VRAM usage by quantization
BF161.9 GBBF16 + full context8.3 GB- Can I run Prism 1 Mini on a Mac?
Prism 1 Mini requires at least 1.9 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 Prism 1 Mini locally?
Yes — Prism 1 Mini can run locally on consumer hardware. At BF16 quantization it needs 1.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Prism 1 Mini?
At BF16, Prism 1 Mini can reach ~2366 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~352 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 ÷ 1.9 × 0.65 = ~2796 tok/s
Estimated speed at BF16 (1.9 GB)
~2796 tok/s~352 tok/s~2796 tok/s~2366 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Prism 1 Mini?
At BF16, the download is about 1.50 GB.
- Which GPUs can run Prism 1 Mini?
50 consumer GPUs can run Prism 1 Mini at BF16 (1.9 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Prism 1 Mini?
59 devices with unified memory can run Prism 1 Mini at BF16 (1.9 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.