LFM2.5 8B A1B needs ~13.2 GB VRAM. Mac Studio M1 Ultra 64GB has 46.1 GB. With Q4_K_M quantization, expect ~207 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
206.8 tok/s
TTFT
936 ms
Safe context
128K
Memory
13.2 GB / 46.1 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 | 206.8 tok/s | 511 ms | 128K |
| Coding | A | Runs well | 206.8 tok/s | 936 ms | 128K |
| Agentic Coding | A | Runs well | 206.8 tok/s | 1362 ms | 128K |
| Reasoning | A | Runs well | 206.8 tok/s | 1107 ms | 128K |
| RAG | A | Runs well | 206.8 tok/s | 1702 ms | 128K |
Inference speed
Estimated decode speed (tokens/sec) for LFM2.5 8B A1B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~508 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 | 507.8 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 324.8 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 324.0 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 277.1 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 261.7 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 258.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 218.1 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 206.8 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 161.7 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 161.7 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 159.9 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 112.8 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 103.4 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 100.5 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 98.8 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 84.0 | Tight |
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 LFM2.5 8B A1B (8.5B params) fits at each quantization level on Mac Studio M1 Ultra 64GB (46.1 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.3 GB | Low | B66 |
Q3_K_S | 3 | 4.2 GB | Low | B66 |
NVFP4 | 4 | 4.8 GB | Medium | B66 |
Q4_K_M | 4 | 5.2 GB | Medium | B66 |
Q5_K_M | 5 | 6.1 GB | High | B66 |
Q6_K | 6 | 7.0 GB | High | B67 |
Q8_0 | 8 | 9.1 GB | Very High | B67 |
F16Best for your GPU | 16 | 17.4 GB | Maximum | B70 |
Copy-paste commands to run LFM2.5 8B A1B on your machine.
Run
lms load LFM2.5-8B-A1B && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 66.5 tok/s | |
| Qwen 3.5 27B | 27B | S | 28.9 tok/s | |
| Qwen 3.6 27B | 27B | S | 21.9 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 55.9 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 68.8 tok/s |
Yes, Mac Studio M1 Ultra 64GB can run LFM2.5 8B A1B with a A grade (Runs well). Expected decode speed: 206.8 tok/s.
LFM2.5 8B A1B (8.5B parameters) requires approximately 13.2 GB of memory with Q4_K_M quantization.
The recommended quantization for LFM2.5 8B A1B is Q4_K_M, which balances quality and memory efficiency.
On Mac Studio M1 Ultra 64GB, LFM2.5 8B A1B achieves approximately 206.8 tokens per second decode speed with a time-to-first-token of 936ms using Q4_K_M quantization.
For coding workloads, LFM2.5 8B A1B on Mac Studio M1 Ultra 64GB receives a A grade with 206.8 tok/s and 128K context.
On Mac Studio M1 Ultra 64GB, LFM2.5 8B A1B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.
Not always. Mac Studio M1 Ultra 64GB 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/lfm2.5-8b-a1b-on-m1-ultra-64gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: