Mradermacher
starcoder2 15b i1 (15B parameters) requires approximately 12.7 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 15 GB of VRAM.
Quick specs
Related models
Inference speed
Estimated decode speed (tokens/sec) for starcoder2 15b i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~131 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 | 131.2 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 83.7 | Fits |
Quick picks
Best hardware
Run this model
Quantization
How much VRAM starcoder2 15b i1 (15B) needs at each GGUF quant, and whether it fits a 24 GB card (RTX 4090 / 3090). The recommended Q4_K_M uses ~9.2 GB — about 43% less VRAM than Q8_0, at a small quality cost.
| Quant | Bits | VRAM (weights) | Quality | Fits 24 GB? |
|---|---|---|---|---|
| Q2_K | 2 | 5.9 GB | Low | Fits |
| Q3_K_S | 3 | 7.4 GB | Low | Fits |
| NVFP4 | 4 | 8.4 GB | Medium | Fits |
| Q4_K_Mrecommended | 4 | 9.2 GB | Medium | Fits |
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
starcoder2 15b i1 (15B parameters) requires approximately 12.7 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, RX 7600 XT 16GB can run starcoder2 15b i1 with a compatibility score of 48/100. It provides 16 GB of memory and achieves approximately 18.3 tokens per second.
The recommended quantization for starcoder2 15b i1 is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for starcoder2 15b i1: RTX A4500 20GB (score: 55/100), RX 7900 XT 20GB (score: 55/100), RTX 4090 24GB (score: 54/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, starcoder2 15b i1 is well-suited for coding. It was designed with these use cases in mind.
See also
| 24 GB |
| Q4_K_M |
| 75.5 |
| Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 71.6 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 68.3 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 60.9 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 50.7 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 48.1 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 34.7 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 34.7 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 26.7 | Heavy offload |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 26.2 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 24.0 | Fits |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 21.2 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 15.7 | Heavy offload |
| RTX 4060 8GB | 8 GB | Q4_K_M | 5.9 | 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.
| Q5_K_M |
| 5 |
| 10.8 GB |
| High |
| Fits |
| Q6_K | 6 | 12.3 GB | High | Fits |
| Q8_0 | 8 | 16.1 GB | Very High | Tight |
| F16 | 16 | 30.7 GB | Maximum | Too big |
VRAM shown is quantized weights only; add ~1–3 GB runtime overhead plus KV cache for your context length. Lower quants trade quality for memory — Q4_K_M is the usual sweet spot; Q2/Q3 only when you must fit a bigger model.
