Llama 2 13B HF — Hardware Requirements & GPU Compatibility
Chat
Llama-2-13b-hf is Meta's 13-billion-parameter base (pretrained, not instruction-tuned) language model from the original Llama 2 family, intended as a general-purpose foundation for natural-language generation and further fine-tuning rather than direct assistant-style chat, for which Meta released separate Llama-2-Chat checkpoints. It is an auto-regressive transformer trained on 2 trillion tokens of publicly available data with a September 2022 knowledge cutoff, using a global batch size of 4 million tokens; unlike the 70B model, the 13B size does not use grouped-query attention. It is a historically significant open-weight release rather than a current state-of-the-art model by 2026 standards. At 13 billion parameters, it fits on a single consumer GPU once quantized. Context length is 4,096 tokens. It is released under the Llama 2 Community License, a custom license that is free for most commercial and research use but requires organizations with more than 700 million monthly active users to request separate permission from Meta. It was published in July 2023.
Runs great on a 24 GB GPU
Runs from 12 GB (Q4_K_M · 16K)Best on 24 GB (Q4_K_M · ~76 tok/s · 32K)Macs from 16 GB (Q4_K_M · ~16 tok/s)
Llama 2 Community
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Llama 2 13B HF
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/TheBloke/Llama-2-13B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 12.5 GB free · 16K context
Download: llama-2-13b.Q4_K_M.gguf7.87 GBTheBloke
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 5070 Ti (16 GB) (4 GB headroom) · Q4_K_M
- Generation speed
- ~68 tok/s
- generation speed
- Cost per 1M output tokens
- $0.69
- per 1M output tokens
How Much VRAM Does Llama 2 13B HF Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 6.1 GB | 12.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~108 tok/s | |
| 6.3 GB | 12.6 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~105 tok/s | |
| 7.0 GB | 13.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~94 tok/s | |
| 7.2 GB | 13.5 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~92 tok/s | |
| 8.6 GB | 14.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~76 tok/s | |
| 10.2 GB | 16.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~64 tok/s | |
| 11.8 GB | 18.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~56 tok/s | |
| 14.3 GB | 20.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~46 tok/s |
Selected Q4_K_M
4-bit medium quantization11.5GBat 16K context
- Weights
- 7.9 GB
- KV cache
- 3.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 12.5 GB free · ~76 tok/s
≥50 tok/s needs ≥660 GB/s · RTX 5090 ~136, RTX 3090 Ti ~76
Which Hardware Can Run Llama 2 13B HF?
Q4_K_M · 8.6 GBLlama 2 13B HF (Q4_K_M) requires 8.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 12+ GB is recommended. 40 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti. 150 devices with unified memory can run Llama 2 13B HF, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M2 Pro (16 GB).
12 GB
12 GB tier →fits · 0.5 GB free · up to 16K ctx
10 GPUs
RTX 3080 Ti~69Simulate output on RTX 3080 TiRTX 5070~51Simulate output on RTX 5070RTX 4070~38Simulate output on RTX 407020 GB
fits · 8.5 GB free · up to 32K ctx
1 GPU
RX 7900 XT~56Simulate output on RX 7900 XT32–40 GB
fits · 20.5 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~136Simulate output on RTX 5090M5 Max36 GB~38Simulate output on Mac Studio M5 Max (36 GB)M532 GB~13Simulate output on MacBook Air 13" M5 (32 GB)Orin~16Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~10Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Llama 2 13B HF?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
The 6 boards that weigh most in the llmrun Score, of 11 with a result for this model; badges show who ran the test.
- MMLU-Pro
TIGER-LabIndependent
Independent25.3%
#127/146 open
- MMLU
Epoch AI · Jul 2023Lab-reported
Lab-reported55.6%
#56/85 open
- BIG-Bench Hard
Epoch AI · Jul 2023Lab-reported
Lab-reported47.0%
#23/38 open
- GSM8K
Epoch AI · Jul 2023Lab-reported
Lab-reported34.3%
#42/62 open
- HellaSwag
Epoch AI · Jul 2023Lab-reported
Lab-reported80.7%
#15/47 open
- ARC Challenge
Epoch AI · Jul 2023Lab-reported
Lab-reported60.3%
#25/56 open
Alternatives to Llama 2 13B HF
Llama 2 family · 11 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Gemma 3 12B ITGoogle | 74.2 | 10.9 GB | ~82 | same size |
| Mistral Nemo Base 2407Mistral AI | — | 11 GB | ~81 | same size |
| Phi 3 Medium 128k InstructMicrosoft | — | 12 GB | ~72 | same size |
| Baichuan2 13B Basebaichuan-inc | — | 11.5 GB | ~76 | same size |
| Vicuna 13B V1.3LMSYS | — | 8.6 GB | ~76 | same size |
| Vllm Translategemma 12B ITchbae624 | — | 9.8 GB | ~73 | same size |
Specifications
- Publisher
- Meta
- Family
- Llama 2
- Parameters
- 13.0B
- Release Date
- 2023-07-13
- License
- Llama 2 Community
Frequently Asked Questions
How much VRAM does Llama 2 13B HF need?
Llama 2 13B HF requires 8.6 GB of VRAM at Q4_K_M, or 28.6 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 13.0B × 4.8 bits ÷ 8 = 7.8 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Llama 2 13B HF?
Yes, at Q8_0 (14.3 GB) or lower. Higher quantizations like BF16 (28.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Llama 2 13B HF?
For Llama 2 13B HF, Q4_K_M (8.6 GB) offers the best balance of quality and VRAM usage. Q5_0 (8.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 6.1 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Llama 2 13B HF on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Llama 2 13B HF. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 8.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Llama 2 13B HF locally?
Yes — Llama 2 13B HF can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Llama 2 13B HF?
At Q4_K_M, Llama 2 13B HF can reach ~559 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~76 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 ÷ 8.6 × 0.65 = ~605 tok/s
Estimated speed at Q4_K_M (8.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Llama 2 13B HF?
At Q4_K_M, the download is about 7.81 GB. The full-precision BF16 version is 26.03 GB. The smallest option (Q2_K) is 5.53 GB.
Which GPUs can run Llama 2 13B HF?
40 consumer GPUs can run Llama 2 13B HF at Q4_K_M. 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 Llama 2 13B HF?
150 devices with unified memory can run Llama 2 13B HF at Q4_K_M (8.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.