Can I run this LLM? — fit by model × hardware

✅ Pick a combination

Computed with the open FitLLM engine — accurate per-layer KV-cache modeling, not a naive estimate. Updated 2026-10-23.

Each page is computed by the open FitLLM engine from official model configs.

By model × hardware

Verdict at Q4_K_M (GPU) / 8-bit (Mac), 32K context: ✅ fits · ⚠️ tight · ❌ won't fit.

Qwen 3.8 27B

Qwen 3.8 2.4T-A95B

Laguna XS 2.1

Laguna S 2.1

Hy3

GLM-5.2

GLM-4.7-Flash

gpt-oss-20b

gpt-oss-120b

Qwen 3.6 35B-A3B

Qwen 3.6 27B

Qwen-AgentWorld-35B-A3B

Gemma 4 31b

Gemma 4 26b A4B

Gemma 4 12b

Llama-3.1-8B-Instruct

Llama-3.2-3B-Instruct

MiniCPM5-1B

Guides

Reference

What can I run on my hardware?

Best GPU / Mac by model

GPU vs GPU

All numbers are computed by the open-source fitllm-engine (MIT) from official model config.json values — reproduce or audit them yourself. Estimates; real usage varies with runtime (llama.cpp / MLX / Ollama), driver and display. Found a mismatch? Report it. · FitLLM home