CodingAI CodingAI Building32.5B
Qwen 2.5 Coder 32B Instruct
Qwen · Apache 2.0
The coding model that defines the builder workflow. Matches GPT-4 on HumanEval. This is what Cursor and Continue.dev users run locally when they want to eliminate API dependency. Apache 2.0 license. The cornerstone of the 'Full AI Builder' profile.
- Parameters
- 32.5B
- Context
- 131,072 tokens
- Released
- 2024-11-12
- Engines
- llama.cpp, ollama, vLLM
- Builder Tools
- Cursor, Continue, Aider, Windsurf, Codex CLI
Qwen 2.5 Coder 32B Instruct (32.5B) requires 21.9 GB VRAM at recommended quality (Q5_K_M). At efficient quality (Q4_K_M), it fits in 18.4 GB VRAM, making it compatible with the NVIDIA GeForce RTX 4060 Ti 16GB. On NVIDIA GeForce RTX 5090, expect approximately 45 tok/s at Q5_K_M. For the best experience, AMD AI Powerhouse ($1,818) is recommended.
— OwnRig methodology, data updated 2026-03-01
VRAM Requirements
| Quality | Quantization | VRAM | File Size |
|---|---|---|---|
| recommended | Q5_K_M | 21.9 GB | 19.5 GB |
| efficient | Q4_K_M | 18.4 GB | 16.3 GB |
| compressed | Q3_K_M | 14.8 GB | 12.7 GB |
| compressed | Q2_K | 11.6 GB | 9.8 GB |
Context Length Impact
KV cache VRAM at Q5_K_M quality. Longer context = more memory.
| Context | KV Cache | Total VRAM |
|---|---|---|
| 2K | 410 MB | 22.3 GB |
| 4K | 819 MB | 22.7 GB |
| 8K | 1.5 GB | 23.4 GB |
| 16K | 3.1 GB | 25 GBexceeds 24 GB |
| 32K | 6.1 GB | 28 GBexceeds 24 GB |
| 64K | 12.3 GB | 34.2 GBexceeds 24 GB |
| 128K | 24.6 GB | 46.5 GBexceeds 24 GB |
Compatible GPUs
Performance data for Qwen 2.5 Coder 32B Instruct across different hardware.
| Device | Quantization | Speed | Rating | Fits in VRAM |
|---|---|---|---|---|
| NVIDIA GeForce RTX 4060 Ti 16GB | Q3_K_M | 10 tok/s | Acceptable | ✓ |
| NVIDIA GeForce RTX 4070 Ti Super | Q3_K_M | 16 tok/s | Acceptable | ✓ |
| NVIDIA GeForce RTX 4090 | Q4_K_M | 25 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 3090 | Q4_K_M | 18 tok/s | Good | ✓ |
| Apple M4 Pro (24GB Unified) | Q4_K_M | 10 tok/s | Acceptable | ✓ |
| Apple M4 Max (36GB Unified) | Q5_K_M | 18 tok/s | Good | ✓ |
| Apple M4 Max (64GB Unified) | Q5_K_M | 18 tok/s | Good | ✓ |
| Apple M4 Max (128GB Unified) | Q8_0 | 15 tok/s | Good | ✓ |
| NVIDIA GeForce RTX 5090 | Q5_K_M | 45 tok/s | Excellent | ✓ |
| Apple M4 Pro (48GB) | Q4_K_M | 10 tok/s | Acceptable | ✓ |
| NVIDIA GeForce RTX 4080 Super | Q3_K_M | 18 tok/s | Acceptable | ✓ |
| NVIDIA GeForce RTX 4060 8GB | Q2_K | — | Not Viable | ✗ (offload) |
| NVIDIA GeForce RTX 4070 Ti 12GB | Q2_K | — | Not Viable | ✗ (offload) |
| NVIDIA GeForce RTX 3080 10GB | Q2_K | — | Not Viable | ✗ (offload) |
| Apple M3 Pro (18GB Unified) | Q3_K_M | — | Not Viable | ✗ (offload) |
Builder Context
Qwen 2.5 Coder 32B Instruct is commonly used with Cursor, Continue, Aider, Windsurf, Codex CLI. For an AI coding workflow, pair it with an embedding model like nomic-embed-text for local RAG.
Recommended Builds
Complete PC builds that can run Qwen 2.5 Coder 32B Instruct.
Mid-Range
High-EndExtreme
High-EndHigh-End
High-End
Mid-Range
Mid-RangeExtreme
Mid-Range
Mid-RangeFull AI Builder
AI Builder Workstation
NVIDIA GeForce RTX 4090 · 64GB DDR5-5600 (2x32GB)
$2,90224 GB VRAM
Runs 10 models
High-EndFull AI Builder
AMD AI Powerhouse
AMD Radeon RX 7900 XTX 24GB · 32GB DDR5-5600 (2x16GB)
$1,81824 GB VRAM
Runs 7 models
Extreme
Extreme AI Workstation
2x NVIDIA GeForce RTX 3090 (Used) · 128GB DDR5-5600 (4x32GB)
$4,17148 GB VRAM
Runs 8 models
High-End
High-End AI Workstation
NVIDIA GeForce RTX 4090 · 64GB DDR5-6000 (2x32GB)
$3,67224 GB VRAM
Runs 8 models
High-EndHome AI Server
High-End Home AI Server
2x NVIDIA GeForce RTX 3090 24GB (Used) + NVLink Bridge · 128GB DDR5-5600 (4x32GB)
$3,84248 GB VRAM
Runs 12 models
High-EndFull AI Builder
Mac Studio AI Builder
Apple M4 Max 128GB (Mac Studio)
$3,999128 GB VRAM
Runs 6 models
Mid-RangePower AI Coding
Mid-Range AI Workstation
NVIDIA GeForce RTX 4060 Ti 16GB · 32GB DDR5-5600 (2x16GB)
$1,22816 GB VRAM
Runs 8 models
Mid-RangeHome AI Server
Mid-Range Home AI Server
NVIDIA GeForce RTX 3090 24GB (Used) · 64GB DDR5-5600 (2x32GB)
$1,89224 GB VRAM
Runs 9 models
ExtremeFull AI Builder
Next-Gen AI Workstation
NVIDIA GeForce RTX 5090 32GB · 64GB DDR5-6000 (2x32GB)
$4,03232 GB VRAM
Runs 6 models
Mid-RangeHome AI Server
Silent Mini-ITX AI Box
NVIDIA GeForce RTX 4060 Ti 16GB · 32GB DDR5-5600 (2x16GB)
$1,25316 GB VRAM
Runs 8 models
Frequently Asked Questions
- How much VRAM does Qwen 2.5 Coder 32B Instruct need?
- Qwen 2.5 Coder 32B Instruct requires 21.9 GB VRAM at recommended quality (Q5_K_M). At lower quality settings, it can fit in as little as 11.6 GB.
- What is the best GPU for Qwen 2.5 Coder 32B Instruct?
- The NVIDIA GeForce RTX 5090 delivers the best performance for Qwen 2.5 Coder 32B Instruct, achieving 45 tok/s at Q5_K_M with an excellent rating.
- Can I run Qwen 2.5 Coder 32B Instruct on an RTX 4060 Ti?
- Yes. On the NVIDIA GeForce RTX 4060 Ti 16GB, Qwen 2.5 Coder 32B Instruct runs at 10 tok/s (Q3_K_M, acceptable).
- What quantization should I use for Qwen 2.5 Coder 32B Instruct?
- For the best quality, use Q5_K_M (21.9 GB VRAM). If your GPU has limited VRAM, Q2_K (11.6 GB) is the most efficient option with acceptable quality.
- Is Qwen 2.5 Coder 32B Instruct good for coding?
- Yes. Qwen 2.5 Coder 32B Instruct is used with Cursor, Continue, Aider, Windsurf, Codex CLI for local AI coding. For the best coding experience, pair it with an embedding model for local RAG.
Data confidence: verified. Last updated: 2026-03-01. Source