What GPU do I need to run amd/AMD-Llama-135m?
134M parameters, published in F32. View on Hugging Face
Set up AMD-Llama-135mAMD-Llama-135m is published by amd on Hugging Face, with 11,663 downloads and 120 likes to date. It's a LlamaForCausalLM model built for text-generation, published natively in F32.
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) |
|---|---|---|---|---|---|
| FP32 | 0.5 GB | 0.6 GB | V100 | 1 | $0.088/hr |
| FP8 (quantized) | 0.1 GB | 0.1 GB | RTX 4070 Super | 1 | $0.121/hr |
| INT4 (quantized) | 0.1 GB | 0.1 GB | RTX 4070 Super | 1 | $0.121/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 AMD-Llama-135m at its published (F32) precision: 1× V100, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
AMD-Llama-135m: 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: 36,864 bytes at 16-bit.
| Context | KV cache, one sequence |
|---|---|
| 2K (model maximum) | 0.07 GB |
Computed from the layer, head and window counts in the model's own configuration (amd/AMD-Llama-135m), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.
AMD-Llama-135m: common questions
How much VRAM does AMD-Llama-135m need?
0.6 GB at FP32, 0.1 GB at FP8 (quantized), 0.1 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 0.5 GB of weights plus inference overhead is the whole requirement.
Can AMD-Llama-135m run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 0.5 GB, or 0.6 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.2 GB, or 0.3 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
How many copies of AMD-Llama-135m fit on one V100?
26, by VRAM alone. That card carries 16.0 GB and one copy needs 0.6 GB at FP32, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 26 copies is not 26 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Alternatives at this size
Other models for text-generation within about a third of AMD-Llama-135m's 134M parameters, from other model lines.
- gpt2 (137M, F32)
- SmolLM2-135M (135M, BF16)
- macbert4csc-base-chinese (102M, F32)
- gpt-neo-125m (150M, F32)
- mamba-130m-hf (129M, F32)
More on AMD-Llama-135m
Fits on an 8 GB GPU at FP32: every model that fits in 8 GB.
Best chat and assistants models: how AMD-Llama-135m ranks against the rest.
Related reading: V100 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.
