Claim Extractor 4B Q 2605 — Hardware Requirements & GPU Compatibility
Chat
Claim Extractor 4B Q 2605 is a 4.7B-parameter open language model from principled-intelligence. It supports a context window of up to 262,144 tokens. At BF16 it needs about 9.79 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 12 GB (BF16 · 64K)Best on 24 GB (BF16 · ~67 tok/s · 256K)Macs from 16 GB (BF16 · ~14 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Claim Extractor 4B 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-4B-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 (2 GB headroom) · BF16
- Generation speed
- ~24 tok/s
- generation speed
- Cost per 1M output tokens
- $0.96
- per 1M output tokens
How Much VRAM Does Claim Extractor 4B Q 2605 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 9.8 GB | 10.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 256K context · ~67 tok/s |
Selected BF16
Brain floating point 1610.0GBat 16K context
- Weights
- 9.3 GB
- KV cache
- 0.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 14.0 GB free · ~67 tok/s
≥50 tok/s needs ≥752 GB/s · RTX 5090 ~119, RTX 3090 Ti ~67
Which Hardware Can Run Claim Extractor 4B Q 2605?
BF16 · 9.8 GBClaim Extractor 4B Q 2605 (BF16) requires 9.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 13+ GB is recommended. Using the full 262K context window can add up to 5.2 GB, bringing total usage to 15.0 GB. 40 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti. 150 devices with unified memory can run Claim Extractor 4B Q 2605, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M2 Pro (16 GB).
12 GB
12 GB tier →fits · 2.0 GB free · up to 64K ctx
10 GPUs
RTX 3080 Ti~61Simulate output on RTX 3080 TiRTX 5070~45Simulate output on RTX 5070RTX 4070~34Simulate output on RTX 407020 GB
fits · 10.0 GB free · up to 256K ctx
1 GPU
RX 7900 XT~49Simulate output on RX 7900 XT32–40 GB
fits · 22.0 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~119Simulate output on RTX 5090M5 Max36 GB~33Simulate output on Mac Studio M5 Max (36 GB)M532 GB~11Simulate output on MacBook Air 13" M5 (32 GB)Orin~14Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~9Simulate 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 4BAlibaba | — | 3.4 GB | ~201 | same size |
| Translategemma 4B ITGoogle | — | 5.5 GB | ~200 | same size |
| Molmo2 4BAllen AI | — | 4.7 GB | ~193 | same size |
| Qwen3 VL 4B InstructAlibaba | — | 4.5 GB | ~208 | same size |
| Agents A1 4BInternScience | — | 3.4 GB | ~205 | same size |
| Qwen3.6 27B MTPLX Optimized SpeedYoussofal | — | 4 GB | ~185 | same size |
Specifications
- Publisher
- principled-intelligence
- Parameters
- 4.7B
- 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 4B Q 2605 need?
Claim Extractor 4B Q 2605 requires 9.8 GB of VRAM at BF16. Full 262K context adds up to 5.2 GB (15.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.7B × 16 bits ÷ 8 = 9.3 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 ≈ 5.7 GB (at full 262K context)
VRAM usage by quantization
Can I run Claim Extractor 4B Q 2605 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Claim Extractor 4B Q 2605. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 9.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Claim Extractor 4B Q 2605 locally?
Yes — Claim Extractor 4B Q 2605 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Claim Extractor 4B Q 2605?
At BF16, Claim Extractor 4B Q 2605 can reach ~490 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~67 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 ÷ 9.8 × 0.65 = ~531 tok/s
Estimated speed at BF16 (9.8 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 4B Q 2605?
At BF16, the download is about 9.32 GB.
Which GPUs can run Claim Extractor 4B Q 2605?
40 consumer GPUs can run Claim Extractor 4B Q 2605 at BF16. Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
Which devices can run Claim Extractor 4B Q 2605?
150 devices with unified memory can run Claim Extractor 4B Q 2605 at BF16 (9.8 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.