G9v3 3B — Hardware Requirements & GPU Compatibility
Chat
G9v3 3B is a 3.0B-parameter open language model from ai9stars. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 2.20 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 · 64K)Best on 24 GB (Q4_K_M · ~298 tok/s · 128K)Macs from 8 GB (Q4_K_M · ~33 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run G9v3 3B
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve ai9stars/G9v3-3B --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 (9 GB headroom) · Q4_K_M
- Generation speed
- ~106 tok/s
- generation speed
- Cost per 1M output tokens
- $0.22
- per 1M output tokens
How Much VRAM Does G9v3 3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.7 GB | 3.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~390 tok/s | |
| 1.9 GB | 3.5 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~350 tok/s | |
| 2.2 GB | 3.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~298 tok/s | |
| 2.5 GB | 4.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 128K context · ~258 tok/s | |
| 2.9 GB | 4.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 128K context · ~228 tok/s | |
| 3.4 GB | 5 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 128K context · ~193 tok/s | |
| 6.4 GB | 8 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~103 tok/s |
Selected Q4_K_M
4-bit medium quantization3.0GBat 16K context
- Weights
- 1.8 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.0 GB free · ~298 tok/s
≥50 tok/s needs ≥169 GB/s · RTX 5090 ~530, RTX 3090 Ti ~298
Which Hardware Can Run G9v3 3B?
Q4_K_M · 2.2 GBG9v3 3B (Q4_K_M) requires 2.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 131K context window can add up to 6.9 GB, bringing total usage to 9.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run G9v3 3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.0 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~225Simulate output on RTX 3080RTX 2080 Ti~182Simulate output on RTX 2080 TiRTX 3070 Ti~180Simulate output on RTX 3070 TiM3*8 GB~33Simulate output on iMac 24" M3 (8 GB)Orin Nano~30Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~22Simulate output on iPhone 1720 GB
fits · 17.0 GB free · up to 128K ctx
1 GPU
RX 7900 XT~218Simulate output on RX 7900 XT32–40 GB
fits · 29.0 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~530Simulate output on RTX 5090M5 Max36 GB~146Simulate output on Mac Studio M5 Max (36 GB)M532 GB~49Simulate output on MacBook Air 13" M5 (32 GB)Orin~61Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~40Simulate 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 |
|---|---|---|---|---|
| SmolLM3 3BHugging Face | — | 3.4 GB | ~285 | same size |
| Llama 3.2 3B InstructMeta | — | 4.1 GB | ~309 | same size |
| Phi 2Microsoft | — | 2.6 GB | ~248 | same size |
| AI21 Jamba Reasoning 3BAI21 Labs | — | 2.3 GB | ~291 | same size |
| Qwen2.5 3B InstructAlibaba | — | 2.8 GB | ~294 | same size |
| Stablelm 3B 4e1tStability AI | — | 3.3 GB | ~247 | same size |
Specifications
- Publisher
- ai9stars
- Parameters
- 3.0B
- Architecture
- LlamaForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 130,560
- Release Date
- 2026-07-21
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does G9v3 3B need?
G9v3 3B requires 2.2 GB of VRAM at Q4_K_M, or 6.4 GB at BF16. Full 131K context adds up to 6.9 GB (9.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.0B × 4.8 bits ÷ 8 = 1.8 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 ≈ 7.3 GB (at full 131K context)
VRAM usage by quantization
What's the best quantization for G9v3 3B?
For G9v3 3B, Q4_K_M (2.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run G9v3 3B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run G9v3 3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run G9v3 3B locally?
Yes — G9v3 3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is G9v3 3B?
At Q4_K_M, G9v3 3B can reach ~2182 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~298 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 ÷ 2.2 × 0.65 = ~2364 tok/s
Estimated speed at Q4_K_M (2.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of G9v3 3B?
At Q4_K_M, the download is about 1.79 GB. The full-precision BF16 version is 5.98 GB. The smallest option (Q2_K) is 1.27 GB.
Which GPUs can run G9v3 3B?
52 consumer GPUs can run G9v3 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 G9v3 3B?
163 devices with unified memory can run G9v3 3B at Q4_K_M (2.2 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.