<!-- Markdown mirror of https://getrigbase.com/models/qwen3-coder-30b-a3b/ . Source of truth is the HTML page. Data licence: CC BY 4.0, please cite RigBase (https://getrigbase.com/models/qwen3-coder-30b-a3b/). -->
Source: https://getrigbase.com/models/qwen3-coder-30b-a3b/
Last updated: 2026-11-17

[Models](https://getrigbase.com/models/) / Qwen3-Coder 30B-A3B

# Best home rig for Qwen3-Coder 30B-A3B

Quick answer

**How much VRAM does Qwen3-Coder 30B-A3B need?**
The weights are about 18.7 GB at Q4_K_M (30.5B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime.

**What is the fastest measured hardware for Qwen3-Coder 30B-A3B?**
RX 9070 16 GB on Windows (HIP): Qwen3-Coder 30B-A3B Q3_K_L at 83.3 tok/s with an 8K prompt, 50.1 at 32K: 83.3 tok/s generation (llama.cpp b11146 (HIP, ROCm 10.0.0), Q3_K_L, q4_0 KV), from https://minjunpark.blog/posts/windows-rx9070-local-llm-benchmarks/.

Last updated: 17 Nov 2026

Legacy model 30.5B total · 3.3B active 2 measured results fastest plain decode: 83.3 tok/s  [model info ↗](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct)

Older model. For current picks see [current models](https://getrigbase.com/models/).

Real, measured generation speeds for Qwen3-Coder 30B-A3B on home hardware, fastest first. Different quants/engines aren't directly comparable.

| Build | Quant | Engine | tok/s | Prompt processing (tok/s) | Cost | Source |
|---|---|---|---|---|---|---|
| [RX 9070 16 GB on Windows (HIP): Qwen3-Coder 30B-A3B Q3_K_L at 83.3 tok/s with an 8K prompt, 50.1 at 32K](https://getrigbase.com/builds/rx-9070-16gb-ryzen-5-7600-qwen3-coder-30b-a3b-q3kl-hip-windows-minjunpark/) | Q3_K_L, q4_0 KV | llama.cpp b11146 (HIP, ROCm 10.0.0) | **83.3** | 1,802 @8K · est. TTFT @8k ≈4.5 s* |  | [minjunpark.blog ↗](https://minjunpark.blog/posts/windows-rx9070-local-llm-benchmarks/) |
| [RX 9070 16 GB on Windows (HIP): Qwen3-Coder 30B-A3B Q3_K_L at 83.3 tok/s with an 8K prompt, 50.1 at 32K](https://getrigbase.com/builds/rx-9070-16gb-ryzen-5-7600-qwen3-coder-30b-a3b-q3kl-hip-windows-minjunpark/) | Q3_K_L, q4_0 KV | llama.cpp b11146 (HIP, ROCm 10.0.0) | **50.1** | 1,790 @32K · est. TTFT @8k ≈4.6 s* |  | [minjunpark.blog ↗](https://minjunpark.blog/posts/windows-rx9070-local-llm-benchmarks/) |

Prompt processing = prefill speed reported by the source, @ prompt length. * est. TTFT @8k is calculated from measured prefill, not measured. [Why it matters](https://getrigbase.com/can-it-run/#prefill).
Ad · this space is available **Sponsor this spot: reach people building local AI rigs.** One clearly-labeled slot per page, no tracking scripts.  [Sponsor this spot →](https://getrigbase.com/advertise/#inquiry)

**Rent before you buy:** try this model on a cloud GPU for a few dollars first: [Runpod](https://runpod.io?ref=77qcpl2c) (referral link; sign up with Google to get the new-user bonus)

## Memory math: how much VRAM / RAM does Qwen3-Coder 30B-A3B need?

Qwen3-Coder 30B-A3B has **30.5B parameters**, about **3.3B active** per token ([source](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct): Qwen model card: 30.5B total / 3.3B activated MoE coding model (2025)). Weight size = parameters × bits-per-weight ÷ 8, before context (KV cache) and runtime overhead.

| Format | Bits/weight | Weights | Smallest common memory size that holds the weights alone |
|---|---|---|---|
| Q8_0 | 8.50 | 32.4 GB | 48 GB |
| Q6_K | 6.56 | 25.0 GB | 32 GB |
| Q5_K_M | 5.70 | 21.7 GB | 24 GB |
| Q4_K_M | 4.89 | **18.7 GB** | 24 GB |
| Q3_K_M | 4.00 | 15.2 GB | 16 GB |
| Q2_K | 3.16 | 12.0 GB | 16 GB |

Bits-per-weight for GGUF quants are llama.cpp's own figures ([llama.cpp quantize README](https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md)). "As measured" rows apply the source's stated bits-per-weight to the parameter count; real files differ slightly because some layers stay at higher precision. Try other combinations in the [VRAM calculator](https://getrigbase.com/can-it-run/).

**Why it can still run on smaller GPUs:** it is a mixture-of-experts model, so only about 3.3B of its 30.5B parameters are used for each generated token. Runtimes such as llama.cpp (--n-cpu-moe), ExLlamaV3 or Project Maya can keep most expert weights in system RAM and only the shared layers and hot experts in VRAM. Then you need **VRAM + system RAM ≥ weights**, and speed is limited mainly by RAM bandwidth.

**Measured on setups with less GPU memory than the Q4_K_M weights** (so part of the model lived in system RAM or was streamed from disk):

- [RX 9070 16GB (16 GB) + about 32 GB](https://getrigbase.com/builds/rx-9070-16gb-ryzen-5-7600-qwen3-coder-30b-a3b-q3kl-hip-windows-minjunpark/): **83.3 tok/s** (Q3_K_L, q4_0 KV)
- [RX 9070 16GB (16 GB) + about 32 GB](https://getrigbase.com/builds/rx-9070-16gb-ryzen-5-7600-qwen3-coder-30b-a3b-q3kl-hip-windows-minjunpark/): **50.1 tok/s** (Q3_K_L, q4_0 KV)

## FAQ

### How much VRAM does Qwen3-Coder 30B-A3B need?

The weights are about 18.7 GB at Q4_K_M (30.5B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime.

### What is the fastest measured hardware for Qwen3-Coder 30B-A3B?

RX 9070 16 GB on Windows (HIP): Qwen3-Coder 30B-A3B Q3_K_L at 83.3 tok/s with an 8K prompt, 50.1 at 32K: 83.3 tok/s generation (llama.cpp b11146 (HIP, ROCm 10.0.0), Q3_K_L, q4_0 KV), from https://minjunpark.blog/posts/windows-rx9070-local-llm-benchmarks/.

Related: [what GPU do you need for 2026 models](https://getrigbase.com/guides/what-gpu-for-qwen3-6-gemma-4-gpt-oss/) · [all builds](https://getrigbase.com/builds/)
