CodeLlama 34B Instruct HF — Hardware Requirements & GPU Compatibility
ChatCode
CodeLlama-34b-Instruct-hf is Meta's 34-billion-parameter instruction-tuned Code Llama model, fine-tuned from the base Code Llama checkpoint for safer, more reliable code-assistant use, as opposed to the plain base and Python-specialized variants in the same family (which also ships in 7B, 13B, and 70B sizes). It is an early, first-generation code model built on the original Llama 2 architecture and predates the later Code Llama 70B release. At 34B parameters, it needs a multi-GPU setup or aggressive quantization for local use. Context length is 16,384 tokens. It is released under the Llama 2 Community License, a custom license that restricts commercial use above 700 million monthly active users, requiring a separate license from Meta, and was published in August 2023.
21.2K downloads
305 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 Instruct HF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 15.0 GB | 17.9 GB | 14.34 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 15.5 GB | 18.3 GB | 14.76 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 17.1 GB | 20.0 GB | 16.45 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 17.6 GB | 20.4 GB | 16.87 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 20.9 GB | 23.8 GB | 20.25 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 24.8 GB | 27.6 GB | 24.04 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 28.5 GB | 31.4 GB | 27.84 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 34.5 GB | 37.3 GB | 33.74 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 CodeLlama 34B Instruct HF?
Q4_K_M · 20.9 GBCodeLlama 34B Instruct 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 Instruct HF?
Q4_K_M · 20.9 GB41 devices with unified memory can run CodeLlama 34B Instruct HF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download CodeLlama 34B Instruct HF
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does CodeLlama 34B Instruct HF need?
CodeLlama 34B Instruct 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 Instruct HF?
Yes, at Q5_K_S (23.9 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 Instruct HF?
For CodeLlama 34B Instruct HF, Q4_K_M (20.9 GB) offers the best balance of quality and VRAM usage. Q5_K_S (23.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 10.0 GB.
VRAM requirement by quantization
IQ2_XXS10.0 GBIQ3_XS14.6 GBQ3_K_M17.1 GBQ4_K_M ★20.9 GBQ5_K_S23.9 GBBF1668.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run CodeLlama 34B Instruct HF on a Mac?
CodeLlama 34B Instruct HF requires at least 10.0 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 CodeLlama 34B Instruct HF locally?
Yes — CodeLlama 34B Instruct 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 Instruct HF?
At Q4_K_M, CodeLlama 34B Instruct 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 ÷ 20.9 × 0.65 = ~248 tok/s
Estimated speed at Q4_K_M (20.9 GB)
~248 tok/s~31 tok/s~248 tok/s~229 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 Instruct HF?
At Q4_K_M, the download is about 20.25 GB. The full-precision BF16 version is 67.49 GB. The smallest option (IQ2_XXS) is 9.28 GB.
- Which GPUs can run CodeLlama 34B Instruct HF?
7 consumer GPUs can run CodeLlama 34B Instruct 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 Instruct HF?
41 devices with unified memory can run CodeLlama 34B Instruct 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.