Yes — with 5.0 GB to spare
Fara 7B at Q4_K_M fits your M4 · 16 GB entirely in unified memory at 8K context, at an estimated 14 tokens per second. Past 99K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.
A web computer-use agent on a Qwen2.5-VL base — it clicks, fills forms and stops for permission. Not a chat model; size it like an 8B with vision.
Hardware requirements What hardware do I need to run Fara 7B? →At Q4_K_M with an 8K context: a 8 GB GPU (RTX 4060 Laptop) 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 | 15.4 GB | 16.5 GB | — | ~4.3 | Reference | 5.8 GB over |
| Q8_0 | 8.2 GB | 9.2 GB | 34K | 8.2 | −0.1% ppl | Long context |
| Q6_K | 6.3 GB | 7.4 GB | 68K | 11 | −0.4% ppl | Long context |
| Q5_K_M | 5.5 GB | 6.5 GB | 84K | 12 | −0.8% ppl | Long context |
| Q4_K_M | 4.7 GB | 5.7 GB | 99K | 14 | −1.9% ppl | Recommended |
| Q3_K_M | 3.8 GB | 4.8 GB | 115K | 18 | −5.4% ppl | Long context |
| Q2_K | 3.2 GB | 4.3 GB | 125K | 21 | −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/Fara-7B-4bit \ --max-tokens 512 --prompt "Hello"
Apple's own array framework. The fastest path on Apple Silicon. More on MLX.
Related models on an M4 · 16 GB
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3 8B 8.19B · similar size |
Q4_K_M · 6.3 GB | 15 | Runs great |
| LFM2.5 8B-A1B 8.47B MoE · similar size |
Q4_K_M · 5.5 GB | 37 | Runs great |
| Llama 3.1 8B Instruct 8.03B · similar size |
Q4_K_M · 6.1 GB | 15 | Runs great |
| Gemma 4 E4B 8.0B · similar size |
Q4_K_M · 5.2 GB | 15 | Runs great |
| Ling 3.0 Tiny 7.9B-A1.3B 7.9B MoE · similar size |
Q4_K_M · 5.1 GB | 43 | Runs great |
| Granite 4.1 8B 8.79B · similar size |
Q4_K_M · 6.8 GB | 14 | Runs great |
| Ministral 3 8B 8.92B · similar size |
Q4_K_M · 6.7 GB | 13 | Runs great |
Fara 7B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
5.7 GB | 33 | Runs great |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
5.7 GB | 47 | Runs great |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
5.7 GB | 131 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
5.7 GB | 125 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
5.7 GB | 48 | Runs great |