What are the best local AI models for 8 GB?
The reviewed models that run well on 8 GB, ranked by each quality source.
Short answer
13models
13 reviewed text models run well on 8 GB, on a graphics card or a Mac. The strongest by each source:
- LMArena: Granite 4.2 3B, Granite 4.2 8B, and Llama 3.1 8B Instruct
- LiveBench: No scored model fits.
- Two separate rankings: the site never mixes them.
Computed from the reviewed catalog with the site's fit rule; scores from LiveBench and LMArena. Methodology
How this list is made
This page is computed from the site's catalog every time it is built, so it moves with the data instead of going stale. It takes every reviewed open text model with a published parameter count and asks the same question the hardware pages ask: does its Q4 file, plus working room and the machine's reserve, fit in fast memory? A model is listed here when it runs well on both reference machines: RTX 4060 · 8 GB VRAM, which keeps 2 GB of the card aside, and Mac mini M2 · 8 GB unified, which keeps 25% of its memory (2 GB) for macOS and your apps.
Quality comes from two sources that are never mixed: LiveBench (2026-06-25), test questions scored 0 to 100, and LMArena (2026-10-22), a rating from blind human votes. Each has its own table below. 8 of the 13 models have neither score yet; they still run well and are in the full table below. How to read the scores.
Top by LMArena
Blind human preference, 2026-10-22 release. Q4 need includes each machine's reserve.
| Model · publisher · parameters | LMArena 2026-10-22 (rating) | Q4 need, card / Mac (GB) |
|---|---|---|
| Granite 4.2 3B IBM · 3B | 1,290 | 5 / 5 |
| Granite 4.2 8B IBM · 8B | 1,290 | 8 / 8 |
| Llama 3.1 8B Instruct Meta · 8B | 1,211 | 8 / 8 |
| Llama 3.2 3B Instruct Meta · 3.2B | 1,167 | 5 / 5 |
| Llama 3.2 1B Instruct Meta · 1.2B | 1,111 | 3 / 3 |
Top by LiveBench
Test questions, 2026-06-25 release, 0–100. Q4 need includes each machine's reserve.
No LiveBench-scored model runs well on 8 GB
Every reviewed model with a LiveBench score needs more memory than these machines offer by the site's estimate. No score is borrowed from a larger sibling.
Every model that runs well
13 reviewed text models, scored or not. Ordered by Hub downloads over 30 days, read 2026-10-25, not by quality; sort a score column to rank by that source alone.
| Llama 3.1 8B Instruct | Not in LiveBench 2026-06-25 | 1,211 | 8 / 8 | 4.9 | Llama 3.1 | 4.8M |
|---|---|---|---|---|---|---|
| Qwen3 1.7B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | 4 / 4 | 1.1 | Apache 2.0 | 4.1M |
| Gemma 4 E4B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | 8 / 8 | 5.0 | Apache 2.0 | 4M |
| Llama 3.2 1B Instruct | Not in LiveBench 2026-06-25 | 1,111 | 3 / 3 | 0.8 | Llama 3.2 | 3.5M |
| Gemma 4 E2B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | 6 / 6 | 3.1 | Apache 2.0 | 3M |
| Qwen3 4B Instruct 2507 | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | 5 / 5 | 2.5 | Apache 2.0 | 2.6M |
| Llama 3.2 3B Instruct | Not in LiveBench 2026-06-25 | 1,167 | 5 / 5 | 2.0 | Llama 3.2 | 1.1M |
| SmolLM3 3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | 5 / 5 | 1.9 | Apache 2.0 | 718.7K |
| Phi-4 mini | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | 5 / 5 | 2.5 | MIT | 342.8K |
| Olmo 3 7B Instruct | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | 8 / 8 | 4.5 | Apache 2.0 | 262.5K |
| Ministral 3 3B | Not in LiveBench 2026-06-25 | Not on the LMArena text leaderboard of 2026-10-22 | 5 / 5 | 2.1 | Apache 2.0 | 87.4K |
| Granite 4.2 8B | Not in LiveBench 2026-06-25 | 1,290 | 8 / 8 | 5.3 | Apache 2.0 | 78.3K |
| Granite 4.2 3B | Not in LiveBench 2026-06-25 | 1,290 | 5 / 5 | 2.2 | Apache 2.0 | 39.8K |
The full lists
Each hardware page lists every model, scored or not, with files and sources.
- RTX 4060 · 8 GB VRAM
- 13 reviewed text models run well24 more run slowly with part of the model in PC RAM (32 GB assumed).
- Mac mini M2 · 8 GB unified
- 13 reviewed text models run wellThe Mac shares this memory with macOS; at this size its reserve, 25% of memory, is 2 GB, the same as the card's, so both need the same for a file.
- More memory
- What are the best local AI models for 16 GB?