EXAONE 3.5 2.4B Instruct — Hardware Requirements & GPU Compatibility
Chat
EXAONE 3.5 2.4B Instruct is a 2.4B-parameter open language model from LGAI-EXAONE in the EXAONE family. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 1.59 GB of VRAM — see which GPUs and Macs can run it below.
61.3K downloads
196 likesSpecifications
- Publisher
- LGAI-EXAONE
- Family
- EXAONE
- Parameters
- 2.4B
- Architecture
- ExaoneForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 102,400
- Release Date
- 2024-12-01
- License
- Other
Get Started
HuggingFace
How Much VRAM Does EXAONE 3.5 2.4B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.1 GB | — | 1.02 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.2 GB | — | 1.05 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 1.3 GB | — | 1.17 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 1.3 GB | — | 1.20 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 1.6 GB | — | 1.44 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 1.9 GB | — | 1.71 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 2.2 GB | — | 1.98 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 2.6 GB | — | 2.41 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run EXAONE 3.5 2.4B Instruct?
Q4_K_M · 1.6 GBEXAONE 3.5 2.4B Instruct (Q4_K_M) requires 1.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run EXAONE 3.5 2.4B Instruct?
Q4_K_M · 1.6 GB59 devices with unified memory can run EXAONE 3.5 2.4B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download EXAONE 3.5 2.4B Instruct
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does EXAONE 3.5 2.4B Instruct need?
EXAONE 3.5 2.4B Instruct requires 1.6 GB of VRAM at Q4_K_M, or 5.3 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.4B × 4.8 bits ÷ 8 = 1.4 GB
KV Cache + Overhead ≈ 0.2 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M1.6 GB- What's the best quantization for EXAONE 3.5 2.4B Instruct?
For EXAONE 3.5 2.4B Instruct, Q4_K_M (1.6 GB) offers the best balance of quality and VRAM usage. Q4_K_L (1.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 0.9 GB.
VRAM requirement by quantization
IQ2_M0.9 GBQ3_K_M1.3 GBIQ4_NL1.5 GBQ4_K_M ★1.6 GBQ5_K_M1.9 GBBF165.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run EXAONE 3.5 2.4B Instruct on a Mac?
EXAONE 3.5 2.4B Instruct requires at least 0.9 GB at IQ2_M, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run EXAONE 3.5 2.4B Instruct locally?
Yes — EXAONE 3.5 2.4B Instruct can run locally on consumer hardware. At Q4_K_M quantization it needs 1.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is EXAONE 3.5 2.4B Instruct?
At Q4_K_M, EXAONE 3.5 2.4B Instruct can reach ~3019 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~412 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 ÷ 1.6 × 0.65 = ~3270 tok/s
Estimated speed at Q4_K_M (1.6 GB)
~3270 tok/s~412 tok/s~3270 tok/s~3019 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of EXAONE 3.5 2.4B Instruct?
At Q4_K_M, the download is about 1.44 GB. The full-precision BF16 version is 4.81 GB. The smallest option (IQ2_M) is 0.81 GB.
- Which GPUs can run EXAONE 3.5 2.4B Instruct?
52 consumer GPUs can run EXAONE 3.5 2.4B Instruct at Q4_K_M (1.6 GB). 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 3.5 2.4B Instruct?
59 devices with unified memory can run EXAONE 3.5 2.4B Instruct at Q4_K_M (1.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.