Can NVIDIA GeForce RTX 4090 run Qwen3 Coder 30B A3B Instruct FP8?

Yes, at Q5_K_M (22.2 GB) or lower. Higher quantizations like Q6_K (25.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Qwen3 Coder 30B A3B Instruct FP8?

For Qwen3 Coder 30B A3B Instruct FP8, Q4_K_M (18.7 GB) offers the best balance of quality and VRAM usage. Q5_K_S (21.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.8 GB.

Can I run Qwen3 Coder 30B A3B Instruct FP8 on a Mac?

Qwen3 Coder 30B A3B Instruct FP8 requires at least 8.8 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 Qwen3 Coder 30B A3B Instruct FP8 locally?

Yes — Qwen3 Coder 30B A3B Instruct FP8 can run locally on consumer hardware. At Q4_K_M quantization it needs 18.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Qwen3 Coder 30B A3B Instruct FP8?

At Q4_K_M, Qwen3 Coder 30B A3B Instruct FP8 can reach ~156 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~35 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

What's the download size of Qwen3 Coder 30B A3B Instruct FP8?

At Q4_K_M, the download is about 18.32 GB. The full-precision Q8_0 version is 30.53 GB. The smallest option (IQ2_XXS) is 8.40 GB.

Alibaba·Qwen·Qwen3MoeForCausalLM

Qwen3 Coder 30B A3B Instruct FP8 — Hardware Requirements & GPU Compatibility

ChatCode

Qwen3 Coder 30B A3B Instruct FP8 is a code-focused mixture-of-experts model from Alibaba with 30.5 billion total parameters and roughly 3 billion active per token, served in FP8 precision. The combination of MoE efficiency and FP8 quantization makes this a remarkably accessible coding assistant that punches well above its effective weight class. Designed for code generation, completion, review, and technical conversation, this model benefits from specialized coding training on top of the Qwen3 MoE architecture. Its low active parameter count means it can run on consumer GPUs with moderate VRAM, making it one of the most hardware-friendly dedicated coding models available.

314.4K downloads 168 likesDec 2025262K context

Specifications

Publisher: Alibaba
Family: Qwen
Parameters: 30.5B
Architecture: Qwen3MoeForCausalLM
Context Length: 262,144 tokens
Vocabulary Size: 151,936
Release Date: 2025-12-03
License: Apache 2.0

Get Started

HuggingFace

Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8

How Much VRAM Does Qwen3 Coder 30B A3B Instruct FP8 Need?

Select a quantization to see compatible GPUs below.

Quantization	Bits	VRAM	+ Context	File Size	Quality
IQ2_XXS	2.20	8.8 GB	21.6 GB	8.40 GB	Importance-weighted 2-bit, extreme compression — significant quality loss
IQ2_M	2.70	10.7 GB	23.5 GB	10.31 GB	Importance-weighted 2-bit, medium
IQ3_XXS	3.10	12.2 GB	25.0 GB	11.83 GB	Importance-weighted 3-bit
Q2_K	3.40	13.4 GB	26.2 GB	12.98 GB	2-bit quantization with K-quant improvements
Q3_K_S	3.50	13.8 GB	26.5 GB	13.36 GB	3-bit small quantization
Q3_K_M	3.90	15.3 GB	28.1 GB	14.89 GB	3-bit medium quantization
Q4_0	4.00	15.7 GB	28.4 GB	15.27 GB	4-bit legacy quantization
IQ4_XS	4.30	16.8 GB	29.6 GB	16.41 GB	Importance-weighted 4-bit, compact
Q4_1	4.50	17.6 GB	30.4 GB	17.18 GB	4-bit legacy quantization with offset
Q4_K_S	4.50	17.6 GB	30.4 GB	17.18 GB	4-bit small quantization
IQ4_NL	4.50	17.6 GB	30.4 GB	17.18 GB	Importance-weighted 4-bit, non-linear
Q4_K_M	4.80	18.7 GB	31.5 GB	18.32 GB	4-bit medium quantization — most popular sweet spot
Q5_K_S	5.50	21.4 GB	34.2 GB	20.99 GB	5-bit small quantization
Q5_K_M	5.70	22.2 GB	34.9 GB	21.76 GB	5-bit medium quantization — good quality/size tradeoff
Q6_K	6.60	25.6 GB	38.4 GB	25.19 GB	6-bit quantization, very good quality
Q8_0	8.00	30.9 GB	43.7 GB	30.53 GB	8-bit quantization, near-lossless

Which GPUs Can Run Qwen3 Coder 30B A3B Instruct FP8?

Q4_K_M · 18.7 GB

Show professional

Qwen3 Coder 30B A3B Instruct FP8 (Q4_K_M) requires 18.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 25+ GB is recommended. Using the full 262K context window can add up to 12.8 GB, bringing total usage to 31.5 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.

Runs great

— Plenty of headroom

NVIDIA GeForce RTX 5090~62 tok/s

Decent

— Enough VRAM, may be tight

NVIDIA GeForce RTX 3090 Ti~35 tok/s NVIDIA GeForce RTX 4090~35 tok/s NVIDIA GeForce RTX 3090~33 tok/s AMD Radeon RX 7900 XTX~28 tok/s AMD Radeon RX 7900 XT~24 tok/s

Which Devices Can Run Qwen3 Coder 30B A3B Instruct FP8?

Q4_K_M · 18.7 GB

21 devices with unified memory can run Qwen3 Coder 30B A3B Instruct FP8, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).

Related Models

Derivatives (2)

Qwen3 Coder 30B A3B Instruct FP8 Q4 K M GGUF Qwen3 Coder 30B A3B Instruct FP8 Q6 K GGUF

Frequently Asked Questions

How much VRAM does Qwen3 Coder 30B A3B Instruct FP8 need?: Qwen3 Coder 30B A3B Instruct FP8 requires 18.7 GB of VRAM at Q4_K_M, or 30.9 GB at Q8_0. Full 262K context adds up to 12.8 GB (31.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 30.5B × 4.8 bits ÷ 8 = 18.3 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 13.2 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M
18.7 GB
Q4_K_M + full context
31.5 GB
Learn more about VRAM estimation →
Can NVIDIA GeForce RTX 4090 run Qwen3 Coder 30B A3B Instruct FP8?: Yes, at Q5_K_M (22.2 GB) or lower. Higher quantizations like Q6_K (25.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Qwen3 Coder 30B A3B Instruct FP8?: For Qwen3 Coder 30B A3B Instruct FP8, Q4_K_M (18.7 GB) offers the best balance of quality and VRAM usage. Q5_K_S (21.4 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 8.8 GB.
VRAM requirement by quantization
IQ2_XXS
8.8 GB~53%
Q3_K_S
13.8 GB~77%
Q4_1
17.6 GB~88%
Q4_K_M ★
18.7 GB~89%
Q5_K_S
21.4 GB~92%
Q8_0
30.9 GB~99%
★ Recommended — best balance of quality and VRAM usage.
Learn more about quantization →
Can I run Qwen3 Coder 30B A3B Instruct FP8 on a Mac?: Qwen3 Coder 30B A3B Instruct FP8 requires at least 8.8 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 Qwen3 Coder 30B A3B Instruct FP8 locally?: Yes — Qwen3 Coder 30B A3B Instruct FP8 can run locally on consumer hardware. At Q4_K_M quantization it needs 18.7 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3 Coder 30B A3B Instruct FP8?: At Q4_K_M, Qwen3 Coder 30B A3B Instruct FP8 can reach ~156 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~35 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 18.7 × 0.55 = ~156 tok/s
Estimated speed at Q4_K_M (18.7 GB)
AMD Instinct MI300X
~156 tok/s
NVIDIA GeForce RTX 4090
~35 tok/s
NVIDIA H100 SXM
~116 tok/s
AMD Instinct MI250X
~96 tok/s
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
Learn more about tok/s estimation →
What's the download size of Qwen3 Coder 30B A3B Instruct FP8?: At Q4_K_M, the download is about 18.32 GB. The full-precision Q8_0 version is 30.53 GB. The smallest option (IQ2_XXS) is 8.40 GB.