LFM2 24B needs ~21.4 GB VRAM. MacBook Pro M4 32GB has 23.0 GB. With Q4_K_M quantization, expect ~10 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
Tight fit
Decode
9.5 tok/s
TTFT
20344 ms
Safe context
27K
Memory
21.4 GB / 23.0 GB
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Tight fit | 9.5 tok/s | 11097 ms | 27K |
| Coding | A | Tight fit | 9.5 tok/s | 20344 ms | 27K |
| Agentic Coding | A | Runs with offload (needs ~0.5 GB host RAM) | 8.9 tok/s | 31772 ms | 27K |
| Reasoning | A | Tight fit | 9.5 tok/s | 24043 ms | 27K |
| RAG | A | Runs with offload (needs ~0.5 GB host RAM) | 8.9 tok/s | 39714 ms | 27K |
Inference speed
Estimated decode speed (tokens/sec) for LFM2 24B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~88 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 88.2 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 56.3 | Tight |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 50.8 | Tight |
| RTX 3090 24GB | 24 GB | Q4_K_M | 48.1 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 40.9 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 36.8 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 36.8 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 34.1 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 32.3 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 23.2 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 21.3 | Too big |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 17.6 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 16.2 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 7.5 | Too big |
| RTX 3060 12GB | 12 GB | Q4_K_M | 4.7 | Too big |
| RTX 4060 8GB | 8 GB | Q4_K_M | 2.2 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How LFM2 24B (24B params) fits at each quantization level on MacBook Pro M4 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 9.4 GB | Low | A82 |
Q3_K_S | 3 | 11.8 GB | Low | A84 |
NVFP4 | 4 | 13.4 GB | Medium | A83 |
Q4_K_M | 4 | 14.6 GB | Medium | A83 |
Q5_K_MBest for your GPU | 5 | 17.3 GB | High | A83 |
Q6_K | 6 | 19.7 GB | High | F0 |
Q8_0 | 8 | 25.7 GB | Very High | F0 |
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 | A | 11.7 tok/s | |
| Qwen 3.5 27B | 27B | S | 8.6 tok/s | |
| Qwen 3.6 27B | 27B | S | 7.1 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 12.4 tok/s | |
| Qwen 3.5 35B A3B | 35B | A | 10.2 tok/s |
Yes, MacBook Pro M4 32GB can run LFM2 24B with a A grade (Tight fit). Expected decode speed: 9.5 tok/s.
LFM2 24B (24B parameters) requires approximately 21.4 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 32GB, LFM2 24B achieves approximately 9.5 tokens per second decode speed with a time-to-first-token of 20344ms using Q4_K_M quantization.
For coding workloads, LFM2 24B on MacBook Pro M4 32GB receives a A grade with 9.5 tok/s and 27K context.
On MacBook Pro M4 32GB, LFM2 24B can safely use up to 27K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Not always. MacBook Pro M4 32GB 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-m4-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: