LFM2 24B needs ~23.2 GB VRAM. MacBook Pro M4 Pro 48GB has 34.6 GB. With Q4_K_M quantization, expect ~23 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
23.2 tok/s
TTFT
8362 ms
Safe context
91K
Memory
23.2 GB / 34.6 GB
This setup is broadly balanced for this model.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 23.2 tok/s | 4561 ms | 91K |
| Coding | S | Runs well | 23.2 tok/s | 8362 ms | 91K |
| Agentic Coding | S | Runs well | 23.2 tok/s | 12162 ms | 91K |
| Reasoning | S | Runs well | 23.2 tok/s | 9882 ms | 91K |
| RAG | S | Runs well | 23.2 tok/s | 15203 ms | 91K |
How LFM2 24B (24B params) fits at each quantization level on MacBook Pro M4 Pro 48GB (34.6 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | A78 |
Q3_K_S | 3 | 11.8 GB | Low | A79 |
NVFP4 | 4 | 13.4 GB | Medium | A80 |
Q4_K_M | 4 | 14.6 GB | Medium | A81 |
Q5_K_M | 5 | 17.3 GB | High | A82 |
Q6_K | 6 | 19.7 GB | High | A82 |
Q8_0Best for your GPU | 8 | 25.7 GB | Very High | A82 |
F16 | 16 | 49.2 GB | Maximum | F0 |
Copy-paste commands to run LFM2 24B on your machine.
Run
ollama run lfm2Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 31.8 tok/s | |
| Qwen 3.5 27B | 27B | S | 22.7 tok/s | |
| Qwen 3.6 27B | 27B | S | 17.3 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 29.4 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 32.9 tok/s |
Yes, MacBook Pro M4 Pro 48GB can run LFM2 24B with a S grade (Runs well). Expected decode speed: 23.2 tok/s.
LFM2 24B (24B parameters) requires approximately 23.2 GB of memory with Q4_K_M quantization.
The recommended quantization for LFM2 24B is Q4_K_M, which balances quality and memory efficiency.
On MacBook Pro M4 Pro 48GB, LFM2 24B achieves approximately 23.2 tokens per second decode speed with a time-to-first-token of 8362ms using Q4_K_M quantization.
For coding workloads, LFM2 24B on MacBook Pro M4 Pro 48GB receives a S grade with 23.2 tok/s and 91K context.
On MacBook Pro M4 Pro 48GB, LFM2 24B can safely use up to 91K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Not always. MacBook Pro M4 Pro 48GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/lfm2-24b-on-m4-pro-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: