EXAONE 4.0 1.2B — Hardware Requirements & GPU Compatibility
Chat
EXAONE 4.0 1.2B is a 1.3B-parameter open language model from LGAI-EXAONE in the EXAONE family. It supports a context window of up to 65,536 tokens. At Q4_K_M it needs about 1.19 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 · ~551 tok/s · 64K)Macs from 8 GB (Q4_K_M · ~60 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run EXAONE 4.0 1.2B
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/LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 21.9 GB free · 16K context
Download: EXAONE-4.0-1.2B-Q4_K_M.gguf0.81 GBLGAI-EXAONE
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (9 GB headroom) · Q4_K_M
- Generation speed
- ~498 tok/s
- generation speed
- Cost per 1M output tokens
- $0.068
- per 1M output tokens
How Much VRAM Does EXAONE 4.0 1.2B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.0 GB | 2.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 64K context · ~676 tok/s | |
| 1.1 GB | 2.9 GB | 3-bit medium — 3-bit medium quantization | Fits: 64K context · ~624 tok/s | |
| 1.1 GB | 3 GB | 4-bit · i-quant compact — Importance-weighted 4-bit, compact | Fits: 64K context · ~590 tok/s | |
| 1.2 GB | 3.1 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 64K context · ~551 tok/s | |
| 1.3 GB | 3.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 64K context · ~489 tok/s | |
| 1.5 GB | 3.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 64K context · ~443 tok/s | |
| 1.7 GB | 3.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 64K context · ~383 tok/s | |
| 3.0 GB | 4.9 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 64K context · ~220 tok/s |
Selected Q4_K_M
4-bit medium quantization2.1GBat 16K context
- Weights
- 0.8 GB
- KV cache
- 1.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.9 GB free · ~551 tok/s
≥50 tok/s needs ≥91 GB/s · RTX 5090 ~979, RTX 3090 Ti ~551
Which Hardware Can Run EXAONE 4.0 1.2B?
Q4_K_M · 1.2 GBEXAONE 4.0 1.2B (Q4_K_M) requires 1.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 66K context window can add up to 3.9 GB, bringing total usage to 5.1 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run EXAONE 4.0 1.2B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.9 GB free · up to 64K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~415Simulate output on RTX 3080RTX 2080 Ti~337Simulate output on RTX 2080 TiRTX 3070 Ti~332Simulate output on RTX 3070 TiM3*8 GB~60Simulate output on iMac 24" M3 (8 GB)Orin Nano~56Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~40Simulate output on iPhone 1720 GB
fits · 17.9 GB free · up to 64K ctx
1 GPU
RX 7900 XT~403Simulate output on RX 7900 XT32–40 GB
fits · 29.9 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~979Simulate output on RTX 5090M5 Max36 GB~271Simulate output on Mac Studio M5 Max (36 GB)M532 GB~90Simulate output on MacBook Air 13" M5 (32 GB)Orin~112Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~74Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to EXAONE 4.0 1.2B
EXAONE family · 3 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.6 ThinkingOpenBMB | — | 1.5 GB | ~580 | same size |
| Llama 3.2 1B InstructMeta | — | 2.3 GB | ~799 | same size |
| Sweep Next Edit 1.5BXenova | — | 1.6 GB | ~551 | same size |
| Ilama 3.2 1Bhmellor | — | 3.3 GB | ~231 | same size |
| T5gemma L L Ul2 ITGoogle | — | 4.3 GB | ~240 | same size |
| Granite 3.0 1B A400m InstructIBM | — | 1.3 GB | ~524 | same size |
Specifications
- Publisher
- LGAI-EXAONE
- Family
- EXAONE
- Parameters
- 1.3B
- Architecture
- Exaone4ForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 102,400
- Release Date
- 2025-07-11
- License
- Other
Frequently Asked Questions
How much VRAM does EXAONE 4.0 1.2B need?
EXAONE 4.0 1.2B requires 1.2 GB of VRAM at Q4_K_M, or 3.0 GB at BF16. Full 66K context adds up to 3.9 GB (5.1 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.3B × 4.8 bits ÷ 8 = 0.8 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 ≈ 4.3 GB (at full 66K context)
VRAM usage by quantization
What's the best quantization for EXAONE 4.0 1.2B?
For EXAONE 4.0 1.2B, Q4_K_M (1.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run EXAONE 4.0 1.2B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run EXAONE 4.0 1.2B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run EXAONE 4.0 1.2B locally?
Yes — EXAONE 4.0 1.2B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is EXAONE 4.0 1.2B?
At Q4_K_M, EXAONE 4.0 1.2B can reach ~4034 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~551 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 ÷ 1.19 × 0.65 = ~4370 tok/s
Estimated speed at Q4_K_M (1.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of EXAONE 4.0 1.2B?
At Q4_K_M, the download is about 0.77 GB. The full-precision BF16 version is 2.56 GB. The smallest option (Q2_K) is 0.54 GB.
Which GPUs can run EXAONE 4.0 1.2B?
52 consumer GPUs can run EXAONE 4.0 1.2B 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 EXAONE 4.0 1.2B?
163 devices with unified memory can run EXAONE 4.0 1.2B at Q4_K_M (1.2 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.