What GPU do I need to run stabilityai/stablelm-2-zephyr-1_6b?
1.6B parameters, published in F16. View on Hugging Face
Set up stablelm-2-zephyr-1_6bstablelm-2-zephyr-1_6b is published by stabilityai on Hugging Face, with 11,271 downloads and 187 likes to date. It's a StableLmForCausalLM model built for text-generation, published natively in F16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP16 | 3.1 GB | 3.7 GB | Quadro M4000 | 1 | $0.058/hr |
| FP8 (quantized) | 1.5 GB | 1.8 GB | RTX 4000 SFF Ada | 1 | $0.198/hr |
| INT4 (quantized) | 0.8 GB | 0.9 GB | RTX 3060 | 1 | $0.110/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run stablelm-2-zephyr-1_6b at its published (F16) precision: 1× Quadro M4000, at $0.058/hr per GPU ($0.058/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
stablelm-2-zephyr-1_6b: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
Multi-head attention: every layer caches keys and values for every head. Cached per token: 196,608 bytes at 16-bit.
| Context | KV cache, one sequence |
|---|---|
| 4K | 0.75 GB |
Computed from the layer, head and window counts in the model's own configuration (stabilityai/stablelm-2-zephyr-1_6b), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
stablelm-2-zephyr-1_6b: common questions
How much VRAM does stablelm-2-zephyr-1_6b need?
3.7 GB at FP16, 1.8 GB at FP8 (quantized), 0.9 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 3.1 GB of weights plus inference overhead is the whole requirement.
How many copies of stablelm-2-zephyr-1_6b fit on one Quadro M4000?
2, by VRAM alone. That card carries 8.0 GB and one copy needs 3.7 GB at FP16, on a live rate of $0.058/hr for the whole card. Throughput is not modelled here, so 2 copies is not 2 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More StableLM models
- stablelm-3b-4e1t (2.8B, BF16)
- stablelm-zephyr-3b (2.8B, BF16)
Alternatives at this size
Other models for text-generation within about a third of stablelm-2-zephyr-1_6b's 1.6B parameters, from other model lines.
- Qwen2.5-1.5B-Instruct (1.5B, BF16)
- Llama-3.2-1B-Instruct (1.2B, BF16)
- OLMo-2-0425-1B (1.5B, F32)
- LFM2.5-1.2B-Instruct (1.2B, BF16)
- SmolLM2-1.7B (1.7B, BF16)
More on stablelm-2-zephyr-1_6b
Fits on an 8 GB GPU at FP16: every model that fits in 8 GB.
Best chat and assistants models: how stablelm-2-zephyr-1_6b ranks against the rest.
Related reading: H100 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
