Qwen2.5 Coder 3B Claude Opus 4.6 Distilled — Hardware Requirements & GPU Compatibility
ChatReasoningCode
Qwen2.5 Coder 3B Claude Opus 4.6 Distilled is a 3.1B-parameter open language model from ryzdfm in the Qwen 2.5 family. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 2.23 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~294 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~32 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve ryzdfm/qwen2.5-coder-3b-claude_opus_4.6-distilled --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 3060 12GB (9 GB headroom) · Q4_K_M
- Generation speed
- ~105 tok/s
- generation speed
- Cost per 1M output tokens
- $0.18
- per 1M output tokens
How Much VRAM Does Qwen2.5 Coder 3B Claude Opus 4.6 Distilled Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 1.7 GB | 2.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~388 tok/s | |
| 1.9 GB | 3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~349 tok/s | |
| 2.2 GB | 3.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~294 tok/s | |
| 2.6 GB | 3.7 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~255 tok/s | |
| 2.9 GB | 4.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~224 tok/s | |
| 3.5 GB | 4.6 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~189 tok/s | |
| 6.5 GB | 7.7 GB | 16-bit · full — Full half-precision — baseline for inference | Fits: 32K context · ~100 tok/s |
Selected Q4_K_M
4-bit medium quantization2.8GBat 16K context
- Weights
- 1.9 GB
- KV cache
- 0.6 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 21.2 GB free · ~294 tok/s
≥50 tok/s needs ≥171 GB/s · RTX 5090 ~522, RTX 3090 Ti ~294
Which Hardware Can Run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled?
Q4_K_M · 2.2 GBQwen2.5 Coder 3B Claude Opus 4.6 Distilled (Q4_K_M) requires 2.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 33K context window can add up to 1.1 GB, bringing total usage to 3.4 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 5.2 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~222Simulate output on RTX 3080RTX 2080 Ti~180Simulate output on RTX 2080 TiRTX 3070 Ti~177Simulate output on RTX 3070 TiM3*8 GB~32Simulate output on iMac 24" M3 (8 GB)Orin Nano~30Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~21Simulate output on iPhone 1720 GB
fits · 17.2 GB free · up to 32K ctx
1 GPU
RX 7900 XT~215Simulate output on RX 7900 XT32–40 GB
fits · 29.2 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~522Simulate output on RTX 5090M5 Max36 GB~144Simulate output on Mac Studio M5 Max (36 GB)M532 GB~48Simulate output on MacBook Air 13" M5 (32 GB)Orin~60Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~39Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Qwen2.5 Coder 3B Claude Opus 4.6 Distilled
Qwen 2.5 family · 43 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| D1 3BLiquid AI | — | 2.6 GB | ~285 | same size |
| Dots.mocrdots-studio | — | 2.6 GB | ~301 | same size |
| Dots.ocrdots-studio | — | 2.6 GB | ~301 | same size |
| SmolLM3 3BHugging Face | — | 3.4 GB | ~285 | same size |
| Llama 3.2 3B InstructMeta | — | 4.1 GB | ~309 | same size |
| Starcoder2 3BBigCode | — | 2.6 GB | ~301 | same size |
Specifications
- Publisher
- ryzdfm
- Family
- Qwen 2.5
- Parameters
- 3.1B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-04-02
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen2.5 Coder 3B Claude Opus 4.6 Distilled need?
Qwen2.5 Coder 3B Claude Opus 4.6 Distilled requires 2.2 GB of VRAM at Q4_K_M, or 6.5 GB at FP16. Full 33K context adds up to 1.1 GB (3.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.1B × 4.8 bits ÷ 8 = 1.9 GB
KV Cache + Overhead ≈ 0.3 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 ≈ 1.5 GB (at full 33K context)
VRAM usage by quantization
What's the best quantization for Qwen2.5 Coder 3B Claude Opus 4.6 Distilled?
For Qwen2.5 Coder 3B Claude Opus 4.6 Distilled, Q4_K_M (2.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.2 GB of usable unified memory (RAM minus macOS overhead).
Can I run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled locally?
Yes — Qwen2.5 Coder 3B Claude Opus 4.6 Distilled can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen2.5 Coder 3B Claude Opus 4.6 Distilled?
At Q4_K_M, Qwen2.5 Coder 3B Claude Opus 4.6 Distilled can reach ~2153 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~294 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 ÷ 2.23 × 0.65 = ~2332 tok/s
Estimated speed at Q4_K_M (2.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen2.5 Coder 3B Claude Opus 4.6 Distilled?
At Q4_K_M, the download is about 1.85 GB. The full-precision FP16 version is 6.17 GB. The smallest option (Q2_K) is 1.31 GB.
Which GPUs can run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled?
52 consumer GPUs can run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled?
163 devices with unified memory can run Qwen2.5 Coder 3B Claude Opus 4.6 Distilled at Q4_K_M (2.2 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.