Claim Extractor 2B Q 2605 — Hardware Requirements & GPU Compatibility
Chat
Claim Extractor 2B Q 2605 is a 2.3B-parameter open language model from principled-intelligence. It supports a context window of up to 262,144 tokens. At BF16 it needs about 4.95 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 128K)Best on 24 GB (BF16 · ~132 tok/s · 256K)Macs from 16 GB (BF16 · ~28 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Claim Extractor 2B Q 2605
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve principled-intelligence/claim-extractor-2B-q-2605 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (6 GB headroom) · BF16
- Generation speed
- ~47 tok/s
- generation speed
- Cost per 1M output tokens
- $0.49
- per 1M output tokens
How Much VRAM Does Claim Extractor 2B Q 2605 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 5.0 GB | 5.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 256K context · ~132 tok/s |
Selected BF16
Brain floating point 165.1GBat 16K context
- Weights
- 4.6 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.0 GB free · ~132 tok/s
≥50 tok/s needs ≥380 GB/s · RTX 5090 ~235, RTX 3090 Ti ~132
Which Hardware Can Run Claim Extractor 2B Q 2605?
BF16 · 5.0 GBClaim Extractor 2B Q 2605 (BF16) requires 5.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 262K context window can add up to 3.1 GB, bringing total usage to 8.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run Claim Extractor 2B Q 2605, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.0 GB free · up to 128K ctx
16 GPUs · 2 device families
RTX 3080~100Simulate output on RTX 3080RTX 2080 Ti~81Simulate output on RTX 2080 TiRTX 3070 Ti~80Simulate output on RTX 3070 TiOrin Nano~13Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~10Simulate output on iPhone 1720 GB
fits · 14.9 GB free · up to 256K ctx
1 GPU
RX 7900 XT~97Simulate output on RX 7900 XT32–40 GB
fits · 26.9 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~235Simulate output on RTX 5090M5 Max36 GB~65Simulate output on Mac Studio M5 Max (36 GB)M532 GB~22Simulate output on MacBook Air 13" M5 (32 GB)Orin~27Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~18Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.5 2BAlibaba | — | 1.9 GB | ~370 | same size |
| Qwen3 VL 2B InstructAlibaba | — | 3.5 GB | ~362 | same size |
| Qwen2 VL 2B InstructAlibaba | — | 2.1 GB | ~390 | same size |
| Kimi K3 DSparkRadixArk | — | 2.2 GB | ~381 | same size |
| EXAONE 3.5 2.4B InstructLGAI-EXAONE | — | 3.4 GB | ~412 | same size |
| Qwen3.8 2Bempero-ai | — | 1.9 GB | ~370 | same size |
Specifications
- Publisher
- principled-intelligence
- Parameters
- 2.3B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-05-14
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Claim Extractor 2B Q 2605 need?
Claim Extractor 2B Q 2605 requires 5.0 GB of VRAM at BF16. Full 262K context adds up to 3.1 GB (8.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.3B × 16 bits ÷ 8 = 4.5 GB
KV Cache + Overhead ≈ 0.5 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 ≈ 3.6 GB (at full 262K context)
VRAM usage by quantization
Can I run Claim Extractor 2B Q 2605 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Claim Extractor 2B Q 2605. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 5.0 GB of usable unified memory (RAM minus macOS overhead).
Can I run Claim Extractor 2B Q 2605 locally?
Yes — Claim Extractor 2B Q 2605 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Claim Extractor 2B Q 2605?
At BF16, Claim Extractor 2B Q 2605 can reach ~970 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~132 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 ÷ 4.95 × 0.65 = ~1051 tok/s
Estimated speed at BF16 (5.0 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Claim Extractor 2B Q 2605?
At BF16, the download is about 4.55 GB.
Which GPUs can run Claim Extractor 2B Q 2605?
52 consumer GPUs can run Claim Extractor 2B Q 2605 at BF16. 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 Claim Extractor 2B Q 2605?
151 devices with unified memory can run Claim Extractor 2B Q 2605 at BF16 (5.0 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.