Yes — with 2.3 GB to spare
Granite 4.1 3B at Q4_K_M fits your M3 · 8 GB entirely in unified memory at 8K context, at an estimated 29 tokens per second. Past 36K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
Dense, small, enterprise-flavoured: tool calling and instruction following, no thinking mode.
Hardware requirements What hardware do I need to run Granite 4.1 3B? →At Q4_K_M with an 8K context: a 6 GB GPU (RTX 3060 Laptop) or a 8 GB Mac (M3). 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 | 6.3 GB | 7.6 GB | — | ~8.8 | Reference | 2.2 GB over |
| Q8_0 | 3.4 GB | 4.6 GB | 18K | 17 | −0.1% ppl | Long context |
| Q6_K | 2.6 GB | 3.8 GB | 28K | 22 | −0.4% ppl | Long context |
| Q5_K_M | 2.2 GB | 3.5 GB | 32K | 25 | −0.8% ppl | Long context |
| Q4_K_M | 1.9 GB | 3.1 GB | 36K | 29 | −1.9% ppl | Recommended |
| Q3_K_M | 1.5 GB | 2.8 GB | 41K | 36 | −5.4% ppl | Long context |
| Q2_K | 1.3 GB | 2.6 GB | 44K | 42 | −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.
How to run it
$ pip install mlx-lm $ mlx_lm.generate --model mlx-community/granite-4.1-3b-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M3 · 8 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Granite 4.1 8B 8.79B · same family |
Q4_K_M · 6.8 GB | — | Won't fit |
| Granite 4.1 30B 28.9B · same family |
Q4_K_M · 18.9 GB | — | Won't fit |
| Llama 3.2 3B Instruct 3.21B · similar size |
Q4_K_M · 3.3 GB | 31 | Runs great |
| Phi-4-mini 3.8B 3.84B · similar size |
Q4_K_M · 3.8 GB | 26 | Runs great |
| Ministral 3 3B 3.85B · similar size |
Q4_K_M · 3.6 GB | 26 | Runs great |
| Qwen3 4B 4.02B · similar size |
Q4_K_M · 4.0 GB | 25 | Runs great |
| LFM2.5 2.6B 2.7B · similar size |
Q4_K_M · 2.2 GB | 37 | Runs great |
Granite 4.1 3B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 3060 Laptop 5.3 GB usable · 336 GB/s |
3.1 GB | 106 | Runs great |
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
3.1 GB | 81 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
3.1 GB | 114 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
3.1 GB | 35 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
3.1 GB | 319 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
3.1 GB | 304 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
3.1 GB | 117 | Runs great |