Yes — with 3.5 GB to spare
Olmo 3 7B Instruct at Q4_K_M fits your M1 · 16 GB entirely in unified memory at 8K context, at an estimated 9.3 tokens per second. Past 35K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Fully open — training data and code included. Full multi-head attention, so its cache is 4× a GQA 7B at the same context.
Hardware requirements What hardware do I need to run Olmo 3 7B Instruct? →At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 13.6 GB | 16.7 GB | — | ~2.8 | Reference | 6.0 GB over |
| Q8_0 | 7.2 GB | 10.3 GB | 11K | 5.3 | −0.1% ppl | Fits |
| Q6_K | 5.6 GB | 8.7 GB | 24K | 6.8 | −0.4% ppl | Long context |
| Q5_K_M | 4.8 GB | 7.9 GB | 30K | 7.9 | −0.8% ppl | Long context |
| Q4_K_M | 4.1 GB | 7.2 GB | 35K | 9.3 | −1.9% ppl | Recommended |
| Q3_K_M | 3.3 GB | 6.4 GB | 42K | 11 | −5.4% ppl | Long context |
| Q2_K | 2.8 GB | 5.9 GB | 46K | 13 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. This model interleaves sliding-window layers (4096 tokens, 8 of 32 layers global), which is why its cache barely grows with context.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/Olmo-3-7B-Instruct-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M1 · 16 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Olmo 3.1 32B Instruct 32.2B · same family |
Q4_K_M · 20.0 GB | — | Won't fit |
| Mistral 7B Instruct v0.3 7.25B · similar size |
Q4_K_M · 5.7 GB | 9.3 | Runs great |
| DeepSeek-R1-Distill-Qwen 7B 7.62B · similar size |
Q4_K_M · 5.3 GB | 8.9 | Runs great |
| Qwen2.5-Coder 7B 7.62B · similar size |
Q4_K_M · 5.3 GB | 8.9 | Runs great |
| Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE · similar size |
Q4_K_M · 5.1 GB | 24 | Runs great |
| Gemma 4 E4B 8.0B · similar size |
Q4_K_M · 5.2 GB | 8.4 | Runs great |
| Llama 3.1 8B Instruct 8.03B · similar size |
Q4_K_M · 6.1 GB | 8.4 | Runs great |
Olmo 3 7B Instruct on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
7.2 GB | ~32 | CPU offload |
| Arc B570 8.8 GB usable · 380 GB/s |
7.2 GB | 56 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
7.2 GB | 53 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
7.2 GB | 16 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
7.2 GB | 149 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
7.2 GB | 142 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
7.2 GB | 54 | Runs great |