Qwen1.5 32B — Hardware Requirements & GPU Compatibility
Chat
Qwen1.5-32B is Alibaba's 32.5-billion-parameter dense base language model, one of eight sizes (0.5B to 72B, plus a 14B mixture-of-experts variant) in the Qwen1.5 series, a beta preview of what became Qwen2. It is a raw pretrained Transformer with SwiGLU activation, QKV attention bias, and group-query attention (added specifically for the 32B and larger sizes), and Alibaba does not recommend using it directly for chat, only as a foundation for further fine-tuning or alignment. At 32.5B parameters it needs a high-end consumer GPU or multi-GPU setup once quantized, more at full precision. Context length is 32,768 tokens, stable across all Qwen1.5 model sizes. It is released under a custom Tongyi Qianwen Research License, free for research and academic use, with commercial deployment requiring a separate license from Alibaba. It was published in April 2024.
Runs well on a 24 GB GPU
Runs from 16 GB (IQ2_M · 16K)Best on 24 GB (Q4_K_M · ~32 tok/s · 8K)Macs from 18 GB (IQ2_XS · ~10 tok/s)
Other
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen1.5 32B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/Qwen1.5-32B-i1-GGUF:Q4_K_MQ4_K_M · needs ~24.1 GB · 16K context
Download: Qwen1.5-32B.i1-Q4_K_M.gguf19.70 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 32 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 5090 (32 GB) (7 GB headroom) · Q4_K_M
- Generation speed
- ~57 tok/s
- generation speed
- Cost per 1M output tokens
- $2.41
- per 1M output tokens
How Much VRAM Does Qwen1.5 32B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.7 GB | 22.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~45 tok/s | |
| 15.1 GB | 23.1 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~44 tok/s | |
| 16.7 GB | 24.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 16K context · ~39 tok/s | |
| 17.1 GB | 25.1 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 16K context · ~38 tok/s | |
| 20.3 GB | 28.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~32 tok/s | |
| 24 GB | 32.1 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~27 tok/s | |
| 27.7 GB | 35.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 31.4 GB | |
| 33.4 GB | 41.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 37.1 GB |
Selected Q4_K_M
4-bit medium quantization24.1GBat 16K context
- Weights
- 19.5 GB
- KV cache
- 4.3 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · fits up to 8K context · ~32 tok/s
≥50 tok/s needs ≥1.56 TB/s · RTX 5090 ~57
Which Hardware Can Run Qwen1.5 32B?
Q4_K_M · 20.3 GBQwen1.5 32B (Q4_K_M) requires 20.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. Using the full 33K context window can add up to 8.1 GB, bringing total usage to 28.4 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Qwen1.5 32B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
Q4_K_M · best fit IQ3_M (19.2 GB)
1 GPU
RX 7900 XT~31Simulate output on RX 7900 XT32–40 GB
fits · 7.9 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~57Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate 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
How good is Qwen1.5 32B?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
This is the single board showing results for this model; badges show who ran the test.
- MMLU
Epoch AI · Feb 2024Lab-reported
Lab-reported74.4%
#22/85 open
Alternatives to Qwen1.5 32B
Qwen family · 28 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Nanbeige4.3 33BNanbeige | — | 23.7 GB | ~32 | 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 |
| NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA | — | 19.3 GB | ~197 | same size |
| Agents A1InternScience | — | 21.5 GB | ~171 | same size |
Specifications
- Publisher
- Alibaba
- Family
- Qwen
- Parameters
- 32.5B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2024-04-01
- License
- Other
Frequently Asked Questions
How much VRAM does Qwen1.5 32B need?
Qwen1.5 32B requires 20.3 GB of VRAM at Q4_K_M, or 65.9 GB at BF16. Full 33K context adds up to 8.1 GB (28.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.5B × 4.8 bits ÷ 8 = 19.5 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 ≈ 8.9 GB (at full 33K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Qwen1.5 32B?
Yes, at Q5_K_M (24 GB) or lower. Higher quantizations like Q6_K (27.7 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Qwen1.5 32B?
For Qwen1.5 32B, Q4_K_M (20.3 GB) offers the best balance of quality and VRAM usage. Q5_K_S (23.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 9.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen1.5 32B on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run Qwen1.5 32B, the smallest at IQ2_XS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.3 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Qwen1.5 32B locally?
Yes — Qwen1.5 32B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen1.5 32B?
At Q4_K_M, Qwen1.5 32B can reach ~236 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~32 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 ÷ 20.3 × 0.65 = ~256 tok/s
Estimated speed at Q4_K_M (20.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen1.5 32B?
At Q4_K_M, the download is about 19.51 GB. The full-precision BF16 version is 65.02 GB. The smallest option (IQ2_XXS) is 8.94 GB.
Which GPUs can run Qwen1.5 32B?
7 consumer GPUs can run Qwen1.5 32B 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 Qwen1.5 32B?
122 devices with unified memory can run Qwen1.5 32B at Q4_K_M (20.3 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.