NuExtract 1.5 — Hardware Requirements & GPU Compatibility
Chat
NuExtract 1.5 is a 3.8B-parameter open language model from numind. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 3.40 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 8K)Best on 24 GB (Q4_K_M · ~193 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~21 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run NuExtract 1.5
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve numind/NuExtract-1.5 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (3 GB headroom) · Q4_K_M
- Generation speed
- ~174 tok/s
- generation speed
- Cost per 1M output tokens
- $0.19
- per 1M output tokens
How Much VRAM Does NuExtract 1.5 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.7 GB | 14.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~240 tok/s | |
| 3.0 GB | 15.1 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~221 tok/s | |
| 3.4 GB | 15.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~193 tok/s | |
| 3.8 GB | 15.9 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~171 tok/s | |
| 4.3 GB | 16.3 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~154 tok/s | |
| 4.9 GB | 17 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~133 tok/s | |
| 8.8 GB | 20.8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~75 tok/s |
Selected Q4_K_M
4-bit medium quantization9.0GBat 16K context
- Weights
- 2.3 GB
- KV cache
- 6.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 15.0 GB free · ~193 tok/s
≥50 tok/s needs ≥261 GB/s · RTX 5090 ~343, RTX 3090 Ti ~193
Which Hardware Can Run NuExtract 1.5?
Q4_K_M · 3.4 GBNuExtract 1.5 (Q4_K_M) requires 3.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 131K context window can add up to 50.7 GB, bringing total usage to 54.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run NuExtract 1.5, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
12 GB
12 GB tier →fits · 3.0 GB free · up to 16K ctx
10 GPUs · 1 device family
RTX 3080 Ti~174Simulate output on RTX 3080 TiRTX 5070~129Simulate output on RTX 5070RTX 4070~96Simulate output on RTX 4070iPhone~16Simulate output on Apple iPhone 17 Pro20 GB
fits · 11.0 GB free · up to 32K ctx
1 GPU
RX 7900 XT~141Simulate output on RX 7900 XT32–40 GB
fits · 23.0 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~343Simulate output on RTX 5090M5 Max36 GB~95Simulate output on Mac Studio M5 Max (36 GB)M532 GB~32Simulate output on MacBook Air 13" M5 (32 GB)Orin~39Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~26Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| NVIDIA Nemotron Labs Dory1.0 4B BF16NVIDIA | — | 5.7 GB | ~214 | same size |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 4B Instruct 2507Alibaba | — | 4.2 GB | ~226 | same size |
| MiniCPM V 4OpenBMB | — | 3.1 GB | ~236 | same size |
| Phi 4 Mini ReasoningMicrosoft | — | 4.8 GB | ~228 | same size |
| Qwen2.5 VL 3B InstructAlibaba | — | 3.2 GB | ~249 | same size |
Specifications
- Publisher
- numind
- Parameters
- 3.8B
- Architecture
- Phi3ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 32,064
- Release Date
- 2024-09-26
- License
- MIT
Frequently Asked Questions
How much VRAM does NuExtract 1.5 need?
NuExtract 1.5 requires 3.4 GB of VRAM at Q4_K_M, or 8.8 GB at BF16. Full 131K context adds up to 50.7 GB (54.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.8B × 4.8 bits ÷ 8 = 2.3 GB
KV Cache + Overhead ≈ 1.1 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 ≈ 51.8 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for NuExtract 1.5?
For NuExtract 1.5, Q4_K_M (3.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run NuExtract 1.5 on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run NuExtract 1.5. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 3.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run NuExtract 1.5 locally?
Yes — NuExtract 1.5 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is NuExtract 1.5?
At Q4_K_M, NuExtract 1.5 can reach ~1412 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~193 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 ÷ 3.4 × 0.65 = ~1529 tok/s
Estimated speed at Q4_K_M (3.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of NuExtract 1.5?
At Q4_K_M, the download is about 2.29 GB. The full-precision BF16 version is 7.64 GB. The smallest option (Q2_K) is 1.62 GB.
Which GPUs can run NuExtract 1.5?
52 consumer GPUs can run NuExtract 1.5 at Q4_K_M. 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 NuExtract 1.5?
163 devices with unified memory can run NuExtract 1.5 at Q4_K_M (3.4 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.