언어부터 이미지, 오픈 웨이트부터 API까지. 기능과 실제 비용을 비교하세요.
다음 아이디어에 맞는 AI를 찾아보세요.
> **PrismML-Eng/Bonsai-demo is the source of truth for running these models.** Where anything here disagrees with it, it is right. For an OpenAI-compatible server, run `python -m mlx_vlm.server --model bonsai2-4b-mlx` and send the sampling settings in each request. For CUDA, CPU, and llama.cpp on Metal, use the GGUF packs of the same weights: **Ternary-Bonsai-2-4B-gguf**.
번역 대기 중 · 원문 표시
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...
번역 대기 중 · 원문 표시
> **PrismML-Eng/Bonsai-demo is the source of truth for running these models.** Where anything here disagrees with it, it is right. For an OpenAI-compatible server, run `python -m mlx_vlm.server --model bonsai2-9b-mlx` and send the sampling settings in each request. For CUDA, CPU, and llama.cpp on Metal, use the GGUF packs of the same weights: **Ternary-Bonsai-2-9B-gguf**.
번역 대기 중 · 원문 표시
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
Prism ML Website | Whitepaper | Demo & Examples | Discord Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) > **\~9.4x** smaller than FP16 (ideal) | **95%** of FP16 intelligence retained | **\~26 tok/s** on an Apple M5 Pro laptop
번역 대기 중 · 원문 표시
Prism ML Website | Whitepaper | Demo & Examples | Discord > **\~9.4x** smaller than FP16 (ideal) | **95%** of FP16 intelligence retained | **\~26 tok/s** on an Apple M5 Pro laptop - **\~7.2 GB** deployed footprint (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - **95% of FP16 intelligence retained**: 80.49 average across 15 thinking-mode benchmarks — a *higher* score than the conventional IQ2_XXS build (72.73) at less than two-thirds of its footprint - **Retains thinking, reasoning, and agentic behavior** deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within two points of full precision (93.40), coding at 85.96, agentic tool use at 74.01 - **End-to-end ternary language weights** across embeddings, attention projections, MLP projections, and LM head, at a *true* 1.71 bits per weight — no high-precision escape hatches behind a low-bit label; the vision tower ships in compact 4-bit HQQ - **262K-token context** on-device, kept practical by the Qwen3.6-27B hybrid-attention backbone (\~75% linear attention) and 4-bit KV-cache quantization - **Custom 2-bit hybrid-attention kernels** on Apple MLX (Python, Swift) and CUDA — packed weights are consumed directly, never expanded back to FP16 - **Ships with a DSpark speculative-decoding drafter layer** trained against the Bonsai 27B target — a lossless **1.34x** decode speedup on the CUDA serving path - **1-bit companion**: also available as 1-bit Bonsai 27B (\~3.9 GB), the phone-class operating point that fits an iPhone 17 Pro Max
번역 대기 중 · 원문 표시
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
기본 정보 등록 · 상세 정보 보완 예정
Q2_0 encodes each weight as a 2-bit code `q in {0, 1, 2, 3}`, dequantized via `w = (q - 1) * scale`. One 128-element block is 34 bytes (2 bytes FP16 scale + 32 bytes of packed 2-bit codes) for an effective **2.125 bits/weight**. The fourth code point (`q = 3`, reconstructing to `+2 * scale`) is reserved for future extensions; for ternary weights it is unused. Q2_0 is effectively lossless for ternary weights — the ternary values land exactly on three of the four 2-bit code points, so quantize/dequantize is bit-exact in the absence of FP16 scale rounding.
번역 대기 중 · 원문 표시
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Prism ML Website | White Paper | Demo & Examples | Discord - **White Paper** - **Demo repo** — examples for serving, benchmarking, and integrating Bonsai - **Discord** — community support and updates - **Kernels**: Q2_0 is not yet in mainline `llama.cpp`. Use our fork at PrismML-Eng/llama.cpp (`prism` branch, default) which adds Q2_0 support for CPU (NEON/generic) and Metal. Upstream PR coming soon. Each weight takes a value from {-1, 0, +1}, with one shared FP16 scale per group of 128 weights:
번역 대기 중 · 원문 표시
> **7.1x** smaller than FP16 | **5.2x** faster on M4 Pro | **27** tok/s on iPhone | runs on Mac, iPhone, iPad The information-theoretic cost is log2(3) ≈ 1.585 bits per weight, plus FP16 group scales (16 bits per 128 weights), for a theoretical minimum of ~1.71 bits/weight. This release uses the MLX 2-bit format, which stores each ternary value in 2 bits plus group scales, for an effective ~2.125 bits/weight. The addition of a zero value compared to binary (1-bit) provides more expressive weight representations, allowing better preservation of model quality under extreme compression.
번역 대기 중 · 원문 표시
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
제공사, 분류, 입출력 조건을 조정하세요. 새 모델이 계속 등록됩니다.
월간 토큰 사용량으로 예상 API 비용을 비교하세요.
수집된 백만 토큰당 USD 요금입니다. 캐시 할인, 구간 요금, 추가 추론 출력, 세금은 제외됩니다. 최신 요금은 출처에서 확인하세요.
입력, 출력, 캐시 요금을 구분하고 동일 작업량으로 비교하세요. 이미지, 음성, 영상은 개수, 시간, 해상도로 과금될 수 있습니다.
반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 제한, 정책을 확인하세요. 자체 호스팅에는 연산 및 유지 비용도 듭니다.
순위는 작업, 버전, 평가 방식에 따라 다릅니다. 실제 업무로 정확도, 지연, 안정성, 비용을 비교하세요.
