HarmBench Llama 2 13B Cls — Hardware Requirements & GPU Compatibility
Chat
HarmBench Llama 2 13B Cls is a 13.0B-parameter open language model from cais in the Llama 2 family. It supports a context window of up to 2,048 tokens. At Q4_K_M it needs about 9.79 GB of VRAM — see which GPUs and Macs can run it below.
117.9K downloads
32 likesSpecifications
- Publisher
- cais
- Family
- Llama 2
- Parameters
- 13.0B
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2024-02-03
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does HarmBench Llama 2 13B Cls Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 7.5 GB | — | 5.53 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 7.7 GB | — | 5.69 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 8.3 GB | — | 6.35 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 8.5 GB | — | 6.51 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 9.8 GB | — | 7.81 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 11.3 GB | — | 9.27 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 12.7 GB | — | 10.74 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 15.0 GB | — | 13.02 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run HarmBench Llama 2 13B Cls?
Q4_K_M · 9.8 GBHarmBench Llama 2 13B Cls (Q4_K_M) requires 9.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 13+ GB is recommended. 40 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run HarmBench Llama 2 13B Cls?
Q4_K_M · 9.8 GB49 devices with unified memory can run HarmBench Llama 2 13B Cls, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download HarmBench Llama 2 13B Cls
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does HarmBench Llama 2 13B Cls need?
HarmBench Llama 2 13B Cls requires 9.8 GB of VRAM at Q4_K_M, or 28.0 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 13.0B × 4.8 bits ÷ 8 = 7.8 GB
KV Cache + Overhead ≈ 2 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M9.8 GB- Can NVIDIA GeForce RTX 4090 run HarmBench Llama 2 13B Cls?
Yes, at Q8_0 (15.0 GB) or lower. Higher quantizations like BF16 (28.0 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for HarmBench Llama 2 13B Cls?
For HarmBench Llama 2 13B Cls, Q4_K_M (9.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (10.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 5.6 GB.
VRAM requirement by quantization
IQ2_XXS5.6 GBQ2_K_S7.2 GBQ3_K_M8.3 GBQ4_K_M ★9.8 GBQ5_K_S10.9 GBBF1628.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run HarmBench Llama 2 13B Cls on a Mac?
HarmBench Llama 2 13B Cls requires at least 5.6 GB at IQ2_XXS, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run HarmBench Llama 2 13B Cls locally?
Yes — HarmBench Llama 2 13B Cls can run locally on consumer hardware. At Q4_K_M quantization it needs 9.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is HarmBench Llama 2 13B Cls?
At Q4_K_M, HarmBench Llama 2 13B Cls can reach ~490 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~67 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 9.8 × 0.65 = ~531 tok/s
Estimated speed at Q4_K_M (9.8 GB)
~531 tok/s~67 tok/s~531 tok/s~490 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of HarmBench Llama 2 13B Cls?
At Q4_K_M, the download is about 7.81 GB. The full-precision BF16 version is 26.03 GB. The smallest option (IQ2_XXS) is 3.58 GB.
- Which GPUs can run HarmBench Llama 2 13B Cls?
40 consumer GPUs can run HarmBench Llama 2 13B Cls at Q4_K_M (9.8 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
- Which devices can run HarmBench Llama 2 13B Cls?
52 devices with unified memory can run HarmBench Llama 2 13B Cls at Q4_K_M (9.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.