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.
27.6K downloads
178 likesSpecifications
- 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
Get Started
HuggingFace
How Much VRAM Does CodeLlama 34B HF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 15.0 GB | 17.9 GB | 14.34 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 17.1 GB | 20.0 GB | 16.45 GB | 3-bit medium quantization |
| Q4_K_Mest. | 4.80 | 20.9 GB | 23.8 GB | 20.25 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 24.8 GB | 27.6 GB | 24.04 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 28.5 GB | 31.4 GB | 27.84 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 34.5 GB | 37.3 GB | 33.74 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 68.2 GB | 71.0 GB | 67.49 GB | Brain floating point 16 — preferred for training |
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 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.
Runs great
— Plenty of headroom
Which Devices Can Run CodeLlama 34B HF?
Q4_K_M · 20.9 GB41 devices with unified memory can run CodeLlama 34B HF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightFrequently 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)
KV Cache + Overhead ≈ 3.6 GB (at full 16K context)
VRAM usage by quantization
Q4_K_M20.9 GBQ4_K_M + full context23.8 GB- 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
Q2_K15.0 GBQ4_K_M ★20.9 GBQ5_K_M24.8 GBQ6_K28.5 GBQ8_034.5 GBBF1668.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run CodeLlama 34B HF on a Mac?
CodeLlama 34B HF requires at least 15.0 GB at Q2_K, 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 CodeLlama 34B HF locally?
Yes — CodeLlama 34B HF can run locally on consumer hardware. At Q4_K_M quantization it needs 20.9 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is CodeLlama 34B HF?
At Q4_K_M, CodeLlama 34B HF can reach ~210 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 ÷ 20.9 × 0.65 = ~248 tok/s
Estimated speed at Q4_K_M (20.9 GB)
~248 tok/s~31 tok/s~248 tok/s~210 tok/sReal-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 (20.9 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run CodeLlama 34B HF?
41 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, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.