Mac · Apple Silicon
M1 with 8 GB: which local LLMs run?
With 8 GB of unified memory, the M1 gives the GPU about 5.3 GB by default (68.25 GB/s): enough for models up to about Gemma 3 4B IT.
- Unified memory8 GB
- GPU usable~5.3 GB
- Bandwidth68.3 GB/s
- GPU cores8
Unified memory is not VRAM: macOS reserves part of it. The limit can be raised with sudo sysctl iogpu.wired_limit_mb=…, at the cost of memory for apps. There is no offload to system RAM — it is the same memory.
- CPU cores
- 8
- GPU cores
- 8
- Bandwidth
- 68.3 GB/s
- Memory configurations
- 8 GB · 16 GB
- Sold in
- MacBook Air, MacBook Pro 13, Mac mini, iMac
- Released
- November 2020
Official specData updated 24 days agoSource: Apple tech specs
What the M1 with 8 GB runs
| Gemma 3 4B ITQ6_K · 8K~4.4 GB · 13–19 tok/s estimate | Excellent |
|---|---|
| Qwen3 1.7BQ8_0 · 8K~3.5 GB · 19–27 tok/s estimate | Excellent |
| Llama 3.2 1B InstructQ8_0 · 8K~2.3 GB · 30–43 tok/s estimate | Excellent |
| Qwen3 0.6BQ8_0 · 8K~2.3 GB · 37–57 tok/s estimate | Excellent |
| Qwen2.5 7B InstructQ3_K_M · 8K~4.9 GB · 11–16 tok/s estimate | Compatible |
| Mistral 7B Instruct v0.3Q3_K_M · 8K~5 GB · 11–16 tok/s estimate | Compatible |
| Qwen3 4BQ5_K_M · 8K~4.7 GB · 13–18 tok/s estimate | Compatible |
| Phi-4 Mini Instruct 3.8BQ6_K · 8K~4.9 GB · 12–17 tok/s estimate | Compatible |
| Llama 3.2 3B InstructQ8_0 · 8K~4.9 GB · 12–16 tok/s estimate | Compatible |
| DeepSeek R1 (671B)Q8_0 · 8K~699 GB · No data | Incompatible |
| Qwen3 235B-A22BQ8_0 · 8K~247 GB · No data | Incompatible |
| gpt-oss-120bMXFP4 · 8K~63 GB · No data | Incompatible |
| Llama 4 Scout 17B-16E InstructQ8_0 · 8K~113 GB · No data | Incompatible |
| Qwen2.5 72B InstructQ8_0 · 8K~79.1 GB · No data | Incompatible |
| Llama 3.3 70B InstructQ8_0 · 8K~76.6 GB · No data | Incompatible |
| DeepSeek R1 Distill Llama 70BQ8_0 · 8K~76.6 GB · No data | Incompatible |
| Mixtral 8x7B InstructQ8_0 · 8K~50 GB · No data | Incompatible |
| Qwen3 32BQ8_0 · 8K~36.8 GB · No data | Incompatible |
| DeepSeek R1 Distill Qwen 32BQ8_0 · 8K~36.8 GB · No data | Incompatible |
| Qwen2.5 32B InstructQ8_0 · 8K~36.8 GB · No data | Incompatible |
| Qwen2.5 Coder 32B InstructQ8_0 · 8K~36.8 GB · No data | Incompatible |
| QwQ 32BQ8_0 · 8K~36.8 GB · No data | Incompatible |
| Qwen3 30B-A3BQ8_0 · 8K~33.2 GB · No data | Incompatible |
| Qwen3 Coder 30B-A3B InstructQ8_0 · 8K~33.2 GB · No data | Incompatible |
| Gemma 3 27B ITQ8_0 · 8K~30 GB · No data | Incompatible |
| Gemma 2 27B ITQ8_0 · 8K~31.4 GB · No data | Incompatible |
| Mistral Small 3.2 24B InstructQ8_0 · 8K~26.4 GB · No data | Incompatible |
| gpt-oss-20bMXFP4 · 8K~12.8 GB · No data | Incompatible |
| Qwen3 14BQ8_0 · 8K~17.3 GB · No data | Incompatible |
| DeepSeek R1 Distill Qwen 14BQ8_0 · 8K~17.6 GB · No data | Incompatible |
| Qwen2.5 14B InstructQ8_0 · 8K~17.6 GB · No data | Incompatible |
| Phi-4 14BQ8_0 · 8K~17.4 GB · No data | Incompatible |
| Mistral Nemo 12B InstructQ8_0 · 8K~14.7 GB · No data | Incompatible |
| Gemma 3 12B ITQ8_0 · 8K~13.9 GB · No data | Incompatible |
| Gemma 2 9B ITQ8_0 · 8K~12.5 GB · No data | Incompatible |
| Qwen3 8BQ8_0 · 8K~10.3 GB · No data | Incompatible |
| Llama 3.1 8B InstructQ8_0 · 8K~10 GB · No data | Incompatible |
| DeepSeek R1 Distill Llama 8BQ8_0 · 8K~10 GB · No data | Incompatible |
For each model, the highest-precision quantization that runs entirely in fast memory; otherwise the one with the best result. Speeds are ranges; "estimate" unless a benchmark exists for this exact hardware.
EstimateData updated 24 days agoSource: Run LLM Locally engine