CodeLlama 7B Instruct HF — Hardware Requirements & GPU Compatibility
ChatCode
CodeLlama 7B Instruct HF is a 6.7B-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 5.42 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 4K)Best on 24 GB (Q4_K_M · ~121 tok/s · 16K)Macs from 16 GB (Q4_K_M · ~26 tok/s)
Llama 2 Community
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run CodeLlama 7B Instruct HF
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run codellama:7b-instruct-q4_K_MQ4_K_M fits fully on the RTX 4090 · 11.1 GB free · 16K context
Download: CodeLlama-7b-Instruct-hf.Q4_K_M.gguf4.08 GBmradermacher
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 5060 Ti 16GB (3 GB headroom) · Q4_K_M
- Generation speed
- ~54 tok/s
- generation speed
- Cost per 1M output tokens
- $0.85
- per 1M output tokens
How Much VRAM Does CodeLlama 7B Instruct HF Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.2 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 16K context · ~155 tok/s | |
| 4.3 GB | — | 3-bit small — 3-bit small quantization | Fits: 16K context · ~152 tok/s | |
| 4.7 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~141 tok/s | |
| 4.7 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 16K context · ~138 tok/s | |
| 5.4 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 16K context · ~121 tok/s | |
| 6.2 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 16K context · ~106 tok/s | |
| 6.9 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 16K context · ~95 tok/s | |
| 8.1 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 16K context · ~81 tok/s |
Selected Q4_K_M
4-bit medium quantization12.9GBat 16K context
- Weights
- 4.1 GB
- KV cache
- 8.6 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 11.1 GB free · ~121 tok/s
≥50 tok/s needs ≥417 GB/s · RTX 5090 ~215, RTX 3090 Ti ~121
Which Hardware Can Run CodeLlama 7B Instruct HF?
Q4_K_M · 5.4 GBCodeLlama 7B Instruct HF (Q4_K_M) requires 5.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 16K context window can add up to 7.5 GB, bringing total usage to 12.9 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run CodeLlama 7B Instruct HF, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
16–18 GB
16–18 GB tier →fits · 3.1 GB free · up to 16K ctx
18 GPUs · 2 Mac classes · 2 device families
RTX 5080~115Simulate output on RTX 5080RTX 5070 Ti~108Simulate output on RTX 5070 TiRTX 4080 SUPER~88Simulate output on RTX 4080 SUPERM516 GB~20Simulate output on MacBook Air 13" M5 (16 GB)M3 Pro*18 GB~19Simulate output on MacBook Pro 14" M3 Pro (18 GB)iPad~20Simulate output on iPad Pro M5 13" (16 GB)Orin NX~12Simulate output on NVIDIA Jetson Orin NX 16GB20 GB
fits · 7.1 GB free · up to 16K ctx
1 GPU
RX 7900 XT~89Simulate output on RX 7900 XT32–40 GB
fits · 19.1 GB free · up to 16K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~215Simulate output on RTX 5090M5 Max36 GB~59Simulate output on Mac Studio M5 Max (36 GB)M532 GB~20Simulate output on MacBook Air 13" M5 (32 GB)Orin~25Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~16Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to CodeLlama 7B Instruct HF
Code Llama family · 4 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Mathstral 7B v0.1Mistral AI | — | 6.8 GB | ~133 | same size |
| Mistral 7B Instruct v0.3Mistral AI | — | 6.8 GB | ~133 | same size |
| CodeQwen1.5 7BAlibaba | — | 5.7 GB | ~137 | same size |
| Starling LM 7B BetaNexusflow | — | 5.7 GB | ~133 | same size |
| Llava 1.5 7B HFllava-hf | — | 5 GB | ~141 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
Specifications
- Publisher
- Meta
- Family
- Code Llama
- Parameters
- 6.7B
- Architecture
- LlamaForCausalLM
- Context Length
- 16,384 tokens
- Vocabulary Size
- 32,016
- Release Date
- 2023-08-24
- License
- Llama 2 Community
Frequently Asked Questions
How much VRAM does CodeLlama 7B Instruct HF need?
CodeLlama 7B Instruct HF requires 5.4 GB of VRAM at Q4_K_M, or 14.8 GB at BF16. Full 16K context adds up to 7.5 GB (12.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 6.7B × 4.8 bits ÷ 8 = 4 GB
KV Cache + Overhead ≈ 1.4 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 ≈ 8.9 GB (at full 16K context)
VRAM usage by quantization
What's the best quantization for CodeLlama 7B Instruct HF?
For CodeLlama 7B Instruct HF, Q4_K_M (5.4 GB) offers the best balance of quality and VRAM usage. Q5_0 (5.6 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 4.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run CodeLlama 7B Instruct HF on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run CodeLlama 7B Instruct HF. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.4 GB of usable unified memory (RAM minus macOS overhead).
Can I run CodeLlama 7B Instruct HF locally?
Yes — CodeLlama 7B Instruct HF can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is CodeLlama 7B Instruct HF?
At Q4_K_M, CodeLlama 7B Instruct HF can reach ~886 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~121 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 ÷ 5.42 × 0.65 = ~959 tok/s
Estimated speed at Q4_K_M (5.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of CodeLlama 7B Instruct HF?
At Q4_K_M, the download is about 4.04 GB. The full-precision BF16 version is 13.48 GB. The smallest option (IQ3_XS) is 2.78 GB.
Which GPUs can run CodeLlama 7B Instruct HF?
52 consumer GPUs can run CodeLlama 7B Instruct HF at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run CodeLlama 7B Instruct HF?
151 devices with unified memory can run CodeLlama 7B Instruct HF at Q4_K_M (5.4 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.