CodeLlama 34B HF — Hardware Requirements & GPU Compatibility
ChatCode
CodeLlama 34B HF is a 33.7B-parameter open language model from Meta in the Code Llama family. It supports a context window of up to 16,384 tokens. At Q4_K_M it needs about 20.95 GB of VRAM — see which GPUs and Macs can run it below.
Usable on a 24 GB GPU
Runs on 24 GB (Q4_K_M · ~31 tok/s · 16K)Macs from 24 GB (Q3_K_M · ~13 tok/s)
Llama 2 Community
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run CodeLlama 34B HF
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve codellama/CodeLlama-34b-hf --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX A6000 (48 GB) (24 GB headroom) · Q4_K_M
- Generation speed
- ~24 tok/s
- generation speed
- Cost per 1M output tokens
- $3.85
- per 1M output tokens
How Much VRAM Does CodeLlama 34B HF Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.0 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 16K context · ~44 tok/s | |
| 17.1 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~38 tok/s | |
| 20.9 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 16K context · ~31 tok/s | |
| 24.8 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 27.6 GB | |
| 28.5 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 31.4 GB | |
| 34.5 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 37.3 GB | |
| 68.2 GB | — | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 71 GB |
Selected Q4_K_M
4-bit medium quantization23.8GBat 16K context
- Weights
- 20.3 GB
- KV cache
- 3.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 0.2 GB free · ~31 tok/s
≥50 tok/s needs ≥1.61 TB/s · RTX 5090 ~56
Which Hardware Can Run CodeLlama 34B HF?
Q4_K_M · 20.9 GBCodeLlama 34B HF (Q4_K_M) requires 20.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 28+ GB is recommended. Using the full 16K context window can add up to 2.8 GB, bringing total usage to 23.8 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 100 devices with unified memory can run CodeLlama 34B HF, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit Q3_K_M (20.0 GB)
1 GPU
RX 7900 XT~28Simulate output on RX 7900 XT32–40 GB
fits · 8.2 GB free · up to 16K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~56Simulate output on RTX 5090M5 Max36 GB~15Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~6Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to CodeLlama 34B HF
Code Llama family · 4 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiniCPM V 4.7 35B A3BOpenBMB | — | 22.1 GB | ~169 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
| Ornith 1.5 35B A3Bornith-ai | — | 22 GB | ~151 | same size |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
Specifications
- Publisher
- Meta
- Family
- Code Llama
- Parameters
- 33.7B
- Architecture
- LlamaForCausalLM
- Context Length
- 16,384 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2023-08-24
- License
- Llama 2 Community
Frequently Asked Questions
How much VRAM does CodeLlama 34B HF need?
CodeLlama 34B HF requires 20.9 GB of VRAM at Q4_K_M, or 68.2 GB at BF16. Full 16K context adds up to 2.8 GB (23.8 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 33.7B × 4.8 bits ÷ 8 = 20.2 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.
KV Cache + Overhead ≈ 3.6 GB (at full 16K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run CodeLlama 34B HF?
Yes, at Q4_K_M (20.9 GB) or lower. Higher quantizations like Q5_K_M (24.8 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for CodeLlama 34B HF?
For CodeLlama 34B HF, Q4_K_M (20.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (24.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 15.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run CodeLlama 34B HF on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run CodeLlama 34B HF, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.9 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run CodeLlama 34B HF locally?
Yes — CodeLlama 34B HF can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is CodeLlama 34B HF?
At Q4_K_M, CodeLlama 34B HF can reach ~229 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~31 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 ÷ 20.95 × 0.65 = ~248 tok/s
Estimated speed at Q4_K_M (20.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of CodeLlama 34B HF?
At Q4_K_M, the download is about 20.25 GB. The full-precision BF16 version is 67.49 GB. The smallest option (Q2_K) is 14.34 GB.
Which GPUs can run CodeLlama 34B HF?
7 consumer GPUs can run CodeLlama 34B HF at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run CodeLlama 34B HF?
100 devices with unified memory can run CodeLlama 34B HF at Q4_K_M (20.9 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.