Qwen3 Coder 480B A35B Instruct — Hardware Requirements & GPU Compatibility
ChatCodeFunctions
Qwen3 Coder 480B A35B Instruct is Alibaba's largest code-specialized model, a massive 480.2-billion-parameter mixture-of-experts system with roughly 35 billion parameters active per token. This is the most powerful open-weight coding model in the Qwen3 family, designed for professional-grade code generation, analysis, and software engineering tasks. Running this model locally is a serious undertaking that requires multi-GPU server-class hardware with several hundred gigabytes of combined VRAM. For users with access to such infrastructure, it offers exceptional code quality and understanding that rivals leading proprietary coding assistants, all while keeping data and computation entirely under local control.
Qwen3 Coder 480B A35B Instruct runs on a 512 GB+ Mac or a multi-GPU server
Best local pick → Mac Studio (M3 Ultra, 512GB) · Q4_K_M · 290.5 GB · ~20 tok/s
Macs from 192 GB (IQ3_XXS · ~27 tok/s)
Score 103.9#47 of 106 open#43 of 102 that fit ≤512 GBApache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
103.9
- 90% range 99.4–108.5
- #47 of 106 open models
- #43 of 102 that fit ≤512 GB
Run Qwen3 Coder 480B A35B Instruct
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
vllm serve Qwen/Qwen3-Coder-480B-A35B-Instruct --max-model-len 16384 --tensor-parallel-size 8Size the nodes from the table above
Download: Q4_K_M/Qwen3-Coder-480B-A35B-Instruct-Q4_K_M-00001-of-00006.gguf290.06 GB + 5 partsunsloth
Ways to runOther ways
each opens step-by-stepRun in cloud
Rent 3× H200 SXM · Q4_K_M
- Estimated hourly price
- ~$10.77/hr
- est., whole server
- GPUs
- 3 GPUs
- 423 GB of VRAM
$5+ bonus for new users
How Much VRAM Does Qwen3 Coder 480B A35B Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 204.6 GB | 208.5 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on Instinct MI325X 256 GB | |
| 210.6 GB | 214.5 GB | 3-bit small — 3-bit small quantization | Runs on Instinct MI325X 256 GB | |
| 234.6 GB | 238.5 GB | 3-bit medium — 3-bit medium quantization | Runs on Instinct MI325X 256 GB | |
| 240.6 GB | 244.5 GB | 4-bit · legacy — 4-bit legacy quantization | Runs on Instinct MI325X 256 GB | |
| 288.6 GB | 292.6 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on 5× H100 SXM 80 GB | |
| 342.7 GB | 346.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on 5× H100 SXM 80 GB | |
| 396.7 GB | 400.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on 6× H100 SXM 80 GB | |
| 480.7 GB | 484.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 7× H100 SXM 80 GB |
Selected Q4_K_M
4-bit medium quantization290.5GBat 16K context
- Weights
- 288.1 GB
- KV cache
- 2.1 GB
- Overhead
- 0.3 GB
Server-class: ~290.5 GB at 16K context · about 5× H100 SXM 80 GB
Which Hardware Can Run Qwen3 Coder 480B A35B Instruct?
Q4_K_M · 288.6 GBQwen3 Coder 480B A35B Instruct (Q4_K_M) requires 288.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 376+ GB is recommended. Using the full 262K context window can add up to 33.0 GB, bringing total usage to 321.7 GB. No consumer GPU has enough memory. 1 device with unified memory can run Qwen3 Coder 480B A35B Instruct, including Mac Studio (M3 Ultra, 512GB).
192+ GB
Q4_K_M · best fit IQ3_XXS (188.4 GB)
6 GPUs · 1 Mac class · 2 device families
B200~165Simulate output on B200B300~165Simulate output on B300Instinct MI350X~66Simulate output on Instinct MI350XM3 Ultra256–512 GB~27Simulate output on Mac Studio (M3 Ultra, 256GB)8x H100 SXM5~238Simulate output on NVIDIA DGX H1008x A100 SXM4~212Simulate output on NVIDIA DGX A100 640GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 128 GB: too small for this model (needs ≥ 146.4 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is Qwen3 Coder 480B A35B Instruct?
The llmrun Score merges 6 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the ≤512 GB tier
- Qwen3 Coder 480B A35B Instruct
- Other models
- Best Score for its VRAM
#43 of 102 that fit ≤512 GB
Each dot is a model at the best quant that fits ≤512 GB. The line steps up to the best Score available at each amount of VRAM; a dot below it is beaten by a model that needs no more memory.
Full ≤512 GB ranking →Benchmarks
The 6 boards that weigh most in the llmrun Score, of 8 with a result for this model; badges show who ran the test.
- SWE-bench Verified
SWE-bench · Aug 2025Independent
Independent69.6%
#6/20 open
- LMArena Text
LMArena · Oct 2026Arena
Arena1387.6
#59/188 open
- Terminal-Bench
Epoch AI · Jul 2025Lab-reported
Lab-reported27.2%
#11/16 open
- LMArena WebDev
LMArena · Oct 2026Arena
Arena1274.8
#48/55 open
- SWE-bench Bash Only
SWE-bench · Aug 2025Independent
Independent55.4%
#4/9 open
- WeirdML
Epoch AI · Jul 2025Independent
Independent41.2%
#20/47 open
In the ≤512 GB class
102 models fit ≤512 GBSame Score, only models that fit ≤512 GB at their best quant: this model's peers by memory need.
- #1
DeepSeek V4.1 Flash 1017DeepSeek
134.4
458.4 GB
- #2
MiMo V2.6 Pro RLXiaomi
133.3
499.3 GB
- #3
MiMo V2.6 Flash RLXiaomi
131.9
186.5 GB
- #4
GLM 5.3Z.ai
130.1
453.8 GB
- #5
DeepSeek V4.1 FlashDeepSeek
129.4
458.4 GB
- #6
Step 5 PreviewStepFun
128.0
407.5 GB
Alternatives to Qwen3 Coder 480B A35B Instruct
Qwen 3 family · 79 models →Official models with an llmrun Score, each answering one question; sizes are each model's default quant (usually Q4_K_M) with a 16K-token context.
Best alternative at this size
Beam 1.0 501B A23B
reflection
- 15.6 higher Score
- 13.5 GB more VRAM
Score 119.5 · 304 GB
Fits in less VRAM
GLM 5.3 Flash
Z.ai
- 20.2 higher Score
- 85.3 GB less VRAM
Score 124.1 · 205.2 GB
Other vendor
DeepSeek V4.1 Flash 1017
DeepSeek
- 30.5 higher Score
- 168 GB more VRAM
Score 134.4 · 458.4 GB
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| MiMo V2.6 Flash RLXiaomi | 131.9 | 186.5 GB | —needs > 24 GB | similar score |
| GLM 5.3Z.ai | 130.1 | 453.8 GB | —needs > 24 GB | similar score |
| DeepSeek V4.1 FlashDeepSeek | 129.4 | 458.4 GB | —needs > 24 GB | similar score |
| Step 5 PreviewStepFun | 128.0 | 407.5 GB | —needs > 24 GB | similar score |
| DeepSeek V4 Flash 0731DeepSeek | 127.6 | 183 GB | —needs > 24 GB | similar score |
| GLM 5.2Z.ai | 122.9 | 453.8 GB | —needs > 24 GB | similar score |
| GLM 5Z.ai | 111.8 | 454.1 GB | —needs > 24 GB | similar score |
| DeepSeek V3.2DeepSeek | 110.4 | 412.7 GB | —needs > 24 GB | similar score |
| NVIDIA Nemotron 3 Ultra 550B A55B BF16NVIDIA | 109.7 | 378.4 GB | —needs > 24 GB | similar score |
| DeepSeek V3.2 ExpDeepSeek | 109.0 | 412.7 GB | —needs > 24 GB | similar score |
Specifications
- Publisher
- Alibaba
- Family
- Qwen 3
- Parameters
- 480.2B
- Active parameters
- 35.5B per token
- Architecture
- Qwen3MoeForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-07-22
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3 Coder 480B A35B Instruct need?
Qwen3 Coder 480B A35B Instruct requires 288.6 GB of VRAM at Q4_K_M, or 960.9 GB at BF16. Full 262K context adds up to 33.0 GB (321.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 480.2B × 4.8 bits ÷ 8 = 288.1 GB
KV Cache + Overhead ≈ 0.5 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 ≈ 33.6 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Qwen3 Coder 480B A35B Instruct?
No — Qwen3 Coder 480B A35B Instruct requires at least 144.6 GB at IQ2_XS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for Qwen3 Coder 480B A35B Instruct?
For Qwen3 Coder 480B A35B Instruct, Q4_K_M (288.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (330.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XS at 144.6 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3 Coder 480B A35B Instruct on a Mac?
Yes — Mac Pro M2 Ultra (192 GB) and 3 other Macs can run Qwen3 Coder 480B A35B Instruct, the smallest at IQ3_XXS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 288.6 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio (M3 Ultra, 512GB).
Can I run Qwen3 Coder 480B A35B Instruct locally?
Yes — Qwen3 Coder 480B A35B Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of Qwen3 Coder 480B A35B Instruct?
At Q4_K_M, the download is about 288.09 GB. The full-precision BF16 version is 960.31 GB. The smallest option (IQ2_XS) is 144.05 GB.
Which GPUs can run Qwen3 Coder 480B A35B Instruct?
No single consumer GPU has enough VRAM to run Qwen3 Coder 480B A35B Instruct at Q4_K_M (288.6 GB). Multi-GPU or professional hardware is required.
Which devices can run Qwen3 Coder 480B A35B Instruct?
1 device with unified memory can run Qwen3 Coder 480B A35B Instruct at Q4_K_M (288.6 GB), including Mac Studio (M3 Ultra, 512GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.