Nanbeige4.1 3B — Hardware Requirements & GPU Compatibility
Chat
Nanbeige4.1 3B is a compact chat model from Nanbeige, a Chinese AI startup focused on building efficient small-scale language models. At just under 4 billion parameters, it is designed to run on virtually any modern GPU or even on CPU, making it one of the more accessible options for users with limited hardware. Despite its small size, it handles basic conversation, simple reasoning, and Chinese-English bilingual tasks, serving as a practical entry point for local LLM experimentation.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 64K)Best on 24 GB (Q4_K_M · ~235 tok/s · 256K)Macs from 8 GB (Q4_K_M · ~26 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Nanbeige4.1 3B
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
ollama run hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUFQ4_K_M fits fully on the RTX 4090 · 20.3 GB free · 16K context
Download: Nanbeige4.1-3B-Q8_0-Q4_K_M.gguf2.36 GBEdge-Quant
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (8 GB headroom) · Q4_K_M
- Generation speed
- ~213 tok/s
- generation speed
- Cost per 1M output tokens
- $0.16
- per 1M output tokens
How Much VRAM Does Nanbeige4.1 3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.1 GB | 4.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~311 tok/s | |
| 2.4 GB | 4.4 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~279 tok/s | |
| 2.8 GB | 4.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~235 tok/s | |
| 3.2 GB | 5.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~202 tok/s | |
| 3.7 GB | 5.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~178 tok/s | |
| 4.4 GB | 6.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~150 tok/s | |
| 8.3 GB | 10.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~79 tok/s |
Selected Q4_K_M
4-bit medium quantization3.7GBat 16K context
- Weights
- 2.4 GB
- KV cache
- 1.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.3 GB free · ~235 tok/s
≥50 tok/s needs ≥214 GB/s · RTX 5090 ~418, RTX 3090 Ti ~235
Which Hardware Can Run Nanbeige4.1 3B?
Q4_K_M · 2.8 GBNanbeige4.1 3B (Q4_K_M) requires 2.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 262K context window can add up to 17.1 GB, bringing total usage to 19.8 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Nanbeige4.1 3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.3 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~177Simulate output on RTX 3080RTX 2080 Ti~144Simulate output on RTX 2080 TiRTX 3070 Ti~142Simulate output on RTX 3070 TiM3*8 GB~26Simulate output on iMac 24" M3 (8 GB)Orin Nano~24Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~17Simulate output on iPhone 1720 GB
fits · 16.3 GB free · up to 256K ctx
1 GPU
RX 7900 XT~172Simulate output on RX 7900 XT32–40 GB
fits · 28.3 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~418Simulate output on RTX 5090M5 Max36 GB~115Simulate output on Mac Studio M5 Max (36 GB)M532 GB~39Simulate output on MacBook Air 13" M5 (32 GB)Orin~48Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~32Simulate 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 |
Fine-tunes & variants(1)
Specifications
- Publisher
- Nanbeige
- Parameters
- 3.9B
- Architecture
- LlamaForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 166,144
- Release Date
- 2026-02-10
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Nanbeige4.1 3B need?
Nanbeige4.1 3B requires 2.8 GB of VRAM at Q4_K_M, or 8.3 GB at BF16. Full 262K context adds up to 17.1 GB (19.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.9B × 4.8 bits ÷ 8 = 2.4 GB
KV Cache + Overhead ≈ 0.4 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 ≈ 17.4 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for Nanbeige4.1 3B?
For Nanbeige4.1 3B, Q4_K_M (2.8 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Nanbeige4.1 3B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Nanbeige4.1 3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.8 GB of usable unified memory (RAM minus macOS overhead).
Can I run Nanbeige4.1 3B locally?
Yes — Nanbeige4.1 3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Nanbeige4.1 3B?
At Q4_K_M, Nanbeige4.1 3B can reach ~1720 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~235 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 ÷ 2.79 × 0.65 = ~1864 tok/s
Estimated speed at Q4_K_M (2.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Nanbeige4.1 3B?
At Q4_K_M, the download is about 2.36 GB. The full-precision BF16 version is 7.87 GB. The smallest option (Q2_K) is 1.67 GB.
Which GPUs can run Nanbeige4.1 3B?
52 consumer GPUs can run Nanbeige4.1 3B 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 Nanbeige4.1 3B?
163 devices with unified memory can run Nanbeige4.1 3B at Q4_K_M (2.8 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.