Mac mini M4 64GBBudget pick
64 GB Unified (+40)
C
Adds memory headroom for longer context windows and future model growth.22.4 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$1,099 MSRP
logos16v2 stablelm2 1.6b i1 needs ~4.8 GB VRAM. RTX 3090 24GB has 24.0 GB. With Q4_K_M quantization, expect ~22 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
22.4 tok/s
TTFT
8643 ms
Safe context
1.7M
Memory
4.8 GB / 24.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 22.4 tok/s | 4714 ms | 1.6M |
| Coding | C | Runs well | 22.4 tok/s | 8643 ms | 1.7M |
| Agentic Coding | C | Runs well | 22.4 tok/s | 12571 ms | 1.7M |
| Reasoning | C | Runs well | 22.4 tok/s | 10214 ms | 1.7M |
| RAG | C | Runs well | 22.4 tok/s | 15714 ms | 1.7M |
Inference speed
Estimated decode speed (tokens/sec) for logos16v2 stablelm2 1.6b i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~30 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 | 30.4 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 25.6 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 25.6 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 22.4 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 22.4 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 22.4 | Fits |
| RTX 4060 8GB | 8 GB | Q4_K_M | 22.4 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 22.4 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 22.4 | Fits |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 22.4 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 22.4 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 22.4 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 22.4 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 22.4 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 22.4 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 22.4 | Fits |
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 logos16v2 stablelm2 1.6b i1 (1.600000023841858B params) fits at each quantization level on RTX 3090 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.6 GB | Low | C43 |
Q3_K_S | 3 | 0.8 GB | Low | C43 |
NVFP4 | 4 | 0.9 GB | Medium | C43 |
Q4_K_M | 4 | 1.0 GB | Medium | C43 |
Q5_K_M | 5 | 1.2 GB | High | C43 |
Q6_K | 6 | 1.3 GB | High | C43 |
Q8_0 | 8 | 1.7 GB | Very High | C44 |
F16Best for your GPU | 16 | 3.3 GB | Maximum | C44 |
Copy-paste commands to run logos16v2 stablelm2 1.6b i1 on your machine.
Run
lms load hf-mradermacher--logos16v2-stablelm2-1-6b-i1-gguf && lms server startUpgrade options
Adds memory headroom for longer context windows and future model growth.
~$1,099 MSRP
Adds memory headroom for longer context windows and future model growth.
~$1,599 MSRP
Yes, RTX 3090 24GB can run logos16v2 stablelm2 1.6b i1 with a C grade (Runs well). Expected decode speed: 22.4 tok/s.
logos16v2 stablelm2 1.6b i1 (1.600000023841858B parameters) requires approximately 4.8 GB of memory with Q4_K_M quantization.
The recommended quantization for logos16v2 stablelm2 1.6b i1 is Q4_K_M, which balances quality and memory efficiency.
On RTX 3090 24GB, logos16v2 stablelm2 1.6b i1 achieves approximately 22.4 tokens per second decode speed with a time-to-first-token of 8643ms using Q4_K_M quantization.
For coding workloads, logos16v2 stablelm2 1.6b i1 on RTX 3090 24GB receives a C grade with 22.4 tok/s and 1.7M context.
On RTX 3090 24GB, logos16v2 stablelm2 1.6b i1 can safely use up to 1.7M tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-mradermacher--logos16v2-stablelm2-1-6b-i1-gguf-on-rtx-3090-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: