SmolLM2 135M Instruct Q2 K GGUF — Hardware Requirements & GPU Compatibility
Chat
9 downloadsSpecifications
- Publisher
- Segilmez06
- Parameters
- 135M
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does SmolLM2 135M Instruct Q2 K GGUF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q3_K_L | 4.10 | 0.1 GB | — | 0.07 GB | 3-bit large quantization |
| Q4_K_M | 4.80 | 0.1 GB | — | 0.08 GB | 4-bit medium quantization — most popular sweet spot |
| Q6_K | 6.60 | 0.1 GB | — | 0.11 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 0.1 GB | — | 0.14 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run SmolLM2 135M Instruct Q2 K GGUF?
Q4_K_M · 0.1 GBSmolLM2 135M Instruct Q2 K GGUF (Q4_K_M) requires 0.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run SmolLM2 135M Instruct Q2 K GGUF?
Q4_K_M · 0.1 GB33 devices with unified memory can run SmolLM2 135M Instruct Q2 K GGUF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does SmolLM2 135M Instruct Q2 K GGUF need?
SmolLM2 135M Instruct Q2 K GGUF requires 0.1 GB of VRAM at Q4_K_M, or 0.1 GB at Q8_0.
VRAM = Weights + KV Cache + Overhead
Weights = 135M × 4.8 bits ÷ 8 = 0.1 GB
VRAM usage by quantization
Q4_K_M0.1 GB- What's the best quantization for SmolLM2 135M Instruct Q2 K GGUF?
For SmolLM2 135M Instruct Q2 K GGUF, Q4_K_M (0.1 GB) offers the best balance of quality and VRAM usage. Q6_K (0.1 GB) provides better quality if you have the VRAM. The smallest option is Q3_K_L at 0.1 GB.
VRAM requirement by quantization
Q3_K_L0.1 GB~86%Q4_K_M ★0.1 GB~89%Q6_K0.1 GB~95%Q8_00.1 GB~99%★ Recommended — best balance of quality and VRAM usage.
- Can I run SmolLM2 135M Instruct Q2 K GGUF on a Mac?
SmolLM2 135M Instruct Q2 K GGUF requires at least 0.1 GB at Q3_K_L, 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 SmolLM2 135M Instruct Q2 K GGUF locally?
Yes — SmolLM2 135M Instruct Q2 K GGUF can run locally on consumer hardware. At Q4_K_M quantization it needs 0.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is SmolLM2 135M Instruct Q2 K GGUF?
At Q4_K_M, SmolLM2 135M Instruct Q2 K GGUF can reach ~32389 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~7280 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 0.1 × 0.55 = ~32389 tok/s
Estimated speed at Q4_K_M (0.1 GB)
AMD Instinct MI300X~32389 tok/sNVIDIA GeForce RTX 4090~7280 tok/sNVIDIA H100 SXM~24209 tok/sAMD Instinct MI250X~20025 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of SmolLM2 135M Instruct Q2 K GGUF?
At Q4_K_M, the download is about 0.08 GB. The full-precision Q8_0 version is 0.14 GB. The smallest option (Q3_K_L) is 0.07 GB.
- Which GPUs can run SmolLM2 135M Instruct Q2 K GGUF?
35 consumer GPUs can run SmolLM2 135M Instruct Q2 K GGUF at Q4_K_M (0.1 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run SmolLM2 135M Instruct Q2 K GGUF?
33 devices with unified memory can run SmolLM2 135M Instruct Q2 K GGUF at Q4_K_M (0.1 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.