A.X 4.0 Light — Hardware Requirements & GPU Compatibility
ChatFunctions
A.X 4.0 Light is a 7.3B-parameter open language model from skt. It supports a context window of up to 16,384 tokens. At Q4_K_M it needs about 4.77 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 · 16K)Best on 24 GB (Q4_K_M · ~137 tok/s · 16K)Macs from 8 GB (IQ3_M · ~20 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run A.X 4.0 Light
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/mykor/A.X-4.0-Light-gguf:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 18.4 GB free · 16K context
Download: A.X-4.0-Light-Q4_K_M.gguf4.44 GBmykor
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (6 GB headroom) · Q4_K_M
- Generation speed
- ~49 tok/s
- generation speed
- Cost per 1M output tokens
- $0.39
- per 1M output tokens
How Much VRAM Does A.X 4.0 Light Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.5 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 16K context · ~187 tok/s | |
| 3.6 GB | — | 3-bit small — 3-bit small quantization | Fits: 16K context · ~183 tok/s | |
| 4.0 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~166 tok/s | |
| 4.0 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 16K context · ~162 tok/s | |
| 4.8 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 16K context · ~137 tok/s | |
| 5.6 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 16K context · ~117 tok/s | |
| 6.4 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 16K context · ~102 tok/s | |
| 7.7 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 16K context · ~85 tok/s |
Selected Q4_K_M
4-bit medium quantization5.6GBat 16K context
- Weights
- 4.4 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 18.4 GB free · ~137 tok/s
≥50 tok/s needs ≥367 GB/s · RTX 5090 ~244, RTX 3090 Ti ~137
Which Hardware Can Run A.X 4.0 Light?
Q4_K_M · 4.8 GBA.X 4.0 Light (Q4_K_M) requires 4.8 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 16K context window can add up to 0.8 GB, bringing total usage to 5.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run A.X 4.0 Light, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 2.4 GB free · up to 16K ctx
16 GPUs · 2 device families
RTX 3080~104Simulate output on RTX 3080RTX 2080 Ti~84Simulate output on RTX 2080 TiRTX 3070 Ti~83Simulate output on RTX 3070 TiOrin Nano~14Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~10Simulate output on iPhone 1720 GB
fits · 14.4 GB free · up to 16K ctx
1 GPU
RX 7900 XT~101Simulate output on RX 7900 XT32–40 GB
fits · 26.4 GB free · up to 16K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~244Simulate output on RTX 5090M5 Max36 GB~68Simulate output on Mac Studio M5 Max (36 GB)M532 GB~23Simulate output on MacBook Air 13" M5 (32 GB)Orin~28Simulate 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 Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen2.5 7B InstructAlibaba | 65.1 | 5.8 GB | ~131 | same size |
| Olmo 3 7B InstructAllen AI | — | 8.4 GB | ~114 | same size |
| Phi Mini MoE InstructMicrosoft | — | 5.4 GB | ~239 | same size |
| Falcon H1 7B InstructTII UAE | — | 6.3 GB | ~130 | same size |
| DeepSeek R1 Distill Qwen 7BDeepSeek | — | 5.8 GB | ~131 | same size |
| Mistral 7B Instruct v0.3Mistral AI | — | 6.8 GB | ~133 | same size |
Specifications
- Publisher
- skt
- Parameters
- 7.3B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 16,384 tokens
- Vocabulary Size
- 102,400
- Release Date
- 2025-07-02
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does A.X 4.0 Light need?
A.X 4.0 Light requires 4.8 GB of VRAM at Q4_K_M, or 14.9 GB at BF16. Full 16K context adds up to 0.8 GB (5.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 7.3B × 4.8 bits ÷ 8 = 4.4 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 ≈ 1.2 GB (at full 16K context)
VRAM usage by quantization
What's the best quantization for A.X 4.0 Light?
For A.X 4.0 Light, Q4_K_M (4.8 GB) offers the best balance of quality and VRAM usage. Q5_0 (5.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 2.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run A.X 4.0 Light on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run A.X 4.0 Light, the smallest at IQ3_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.8 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run A.X 4.0 Light locally?
Yes — A.X 4.0 Light can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is A.X 4.0 Light?
At Q4_K_M, A.X 4.0 Light can reach ~1006 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~137 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 ÷ 4.77 × 0.65 = ~1090 tok/s
Estimated speed at Q4_K_M (4.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of A.X 4.0 Light?
At Q4_K_M, the download is about 4.36 GB. The full-precision BF16 version is 14.52 GB. The smallest option (IQ2_XXS) is 2.00 GB.
Which GPUs can run A.X 4.0 Light?
52 consumer GPUs can run A.X 4.0 Light 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 A.X 4.0 Light?
151 devices with unified memory can run A.X 4.0 Light at Q4_K_M (4.8 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.