Free Interactive Tool

Local Model Recommender — which LLM should you run?

Not sure which local LLM is right for your hardware? Answer 5 quick questions and get a personalized model recommendation with download links, VRAM estimates, and expected performance.

Example recommendation (8GB GPU, code generation)

DeepSeek Coder 6.7B (Q4_K_M)
Best for: Code generation · 8GB VRAM · Medium quality
Size
6.7B
VRAM
~4.5 GB
Speed
~50 tok/s

Example output — your results will vary based on your answers.

Table of Contents

How to choose a local model

Picking the right local LLM comes down to three factors: your hardware, your use case, and your quality requirements. Here's how to think about each.

Hardware is the gatekeeper. Your GPU VRAM or system RAM determines the maximum model size you can run. A 7B model at Q4 needs ~5GB. A 30B model at Q4 needs ~18GB. A 70B model at Q4 needs ~42GB. If your hardware can't fit the weights plus KV cache, the model simply won't load. Use the VRAM calculator for precise estimates.

Use case determines model family. Not all models are good at everything. Llama 3.1 excels at general chat and creative writing. DeepSeek Coder is purpose-built for code generation. Mistral has strong function calling for agent workflows. Qwen 2.5 is the best choice for Arabic and multilingual tasks. Pick the family that matches your primary workload.

Quality vs speed is a sliding scale. Quantization shrinks models by reducing the precision of weights. Q8 is nearly lossless but saves only 50%. Q4 saves 75% memory with minimal quality loss (1-3% on benchmarks). Q2 saves 87.5% but quality degradation is noticeable, especially for reasoning and math. Start with Q4 and adjust based on your experience.

Context length adds VRAM. The KV cache for a 7B model at 4K context uses ~1GB. At 128K context it uses ~32GB — often more than the model weights themselves. If you need long context, make sure your hardware can handle the KV cache overhead, or choose a model with efficient attention like the MQA/GQA architectures used in Llama 3.1 and Qwen 2.5.

Model size vs hardware requirements

Updated Jul 2026 — estimates include model weights + 4K KV cache + ~15% overhead

ModelParamsFP16Q8Q4Q2Min hardware
Llama 3.2 3B3B6 GB3.5 GB2.2 GB1.5 GBCPU / 4GB GPU
Qwen 2.5 Coder 1.5B1.5B3 GB2 GB1.2 GB0.8 GBCPU / any GPU
Gemma 2 2B2B4 GB2.5 GB1.6 GB1 GBCPU / 4GB GPU
Mistral 7B7B14 GB8 GB5 GB3 GB8GB GPU / M1
Llama 3.1 8B8B16 GB9 GB5.5 GB3.5 GB8GB GPU / M1
DeepSeek Coder 6.7B6.7B13 GB7.5 GB4.5 GB3 GB8GB GPU / M1
Qwen 2.5 7B7B14 GB8 GB5 GB3 GB8GB GPU / M1
Phi-3 Medium 14B14B28 GB15 GB8 GB5 GB16GB GPU / M4 Pro
Llama 3.1 13B13B26 GB14 GB8 GB5 GB16GB GPU / M4 Pro
Qwen 2.5 32B32B64 GB34 GB18 GB11 GB24GB GPU / multi-GPU
DeepSeek Coder 33B33B66 GB35 GB19 GB12 GB24GB GPU / multi-GPU
Llama 3.1 70B70B140 GB75 GB40 GB22 GBMulti-GPU / A100
Qwen 2.5 72B72B144 GB77 GB41 GB23 GBMulti-GPU / A100
Mixtral 8x7B47B94 GB50 GB28 GB16 GB24GB+ GPU

Quantization guide

Quantization reduces model precision to save memory and increase speed. Here's what you need to know about each level:

LevelBitsMemory savingsQualitySpeedWhen to use
FP1616ReferenceDatacenter GPUs / A100
FP8850%Near-lossless1.5-2×H100/H200 native
Q8850%Excellent (<0.5% loss)1.3×16GB+ GPUs, Apple Silicon
Q6662.5%Very good (~1% loss)1.4×Good balance for 16GB GPUs
Q4475%Good (1-3% loss)1.8×Sweet spot — most users
Q3381%Fair (3-5% loss)Low-memory GPUs (8GB)
Q2287.5%Degraded (5-10% loss)Edge / last resort only

Pro tip: GGUF Q4_K_M is the most popular quantization variant — it uses 4-bit quantization with "importance" weighting that preserves more quality on critical weights. It's llama.cpp's recommended default and works on CPU, Apple Silicon, and GPU.

Frequently asked questions

How do I choose the right local LLM?

Start with your hardware: GPU VRAM is the most important factor (weights + KV cache must fit). Then consider your use case (chat, code, RAG, agent) to pick the right model family. Quantization lets you fit larger models into limited memory at a small quality cost. Use this interactive recommender to find the best match.

How much does quantization affect model quality?

Q8 is near-lossless (<0.5% perplexity increase). Q4 loses ~1-3% on benchmarks — the sweet spot for most users. Q2 loses ~5-10% quality, most noticeable in reasoning and math. For production use, Q4 is recommended. For maximum quality with enough hardware, FP16 is best.

Can I run a 70B model on a consumer GPU?

A 70B model at Q4 requires ~42GB VRAM — too much for a single consumer GPU (RTX 4090 has 24GB). At Q2 it needs ~22GB, fitting on a 24GB card with quality loss. For 70B+ models, you need multi-GPU setup, a datacenter GPU (A100 80GB), or use cloud inference via Plugsky.

What's the best model for code generation on 8GB VRAM?

For 8GB VRAM, DeepSeek Coder 6.7B at Q4 (~4.5GB with KV cache) is the best option for code. Qwen 2.5 Coder 7B at Q4 is also excellent. Both support 16K+ context and outperform much larger models on coding benchmarks. Use Ollama to run them locally.

What if I don't have enough hardware for local models?

You have three options: (1) use more aggressive quantization to fit models in less memory, (2) offload layers to system RAM via llama.cpp CPU+GPU mode, (3) use Plugsky cloud inference — run any model on cloud GPUs with no local hardware requirements and flat monthly pricing from $20/mo.

Last updated Jul 2026. Model availability and performance verified at time of writing — check Ollama and Hugging Face for latest versions.

Don't have enough hardware?

Run any model on cloud GPUs through Plugsky. No hardware limits, flat pricing.

Start free → API docs