EuroLLM 9B Instruct 2512 — Hardware Requirements & GPU Compatibility
Chat
EuroLLM 9B Instruct 2512 is a 9.2B-parameter open language model from utter-project. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 6.14 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 · 8K)Best on 24 GB (Q4_K_M · ~107 tok/s · 32K)Macs from 16 GB (Q4_K_M · ~23 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run EuroLLM 9B Instruct 2512
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 utter-project/EuroLLM-9B-Instruct-2512 --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (3 GB headroom) · Q4_K_M
- Generation speed
- ~97 tok/s
- generation speed
- Cost per 1M output tokens
- $0.35
- per 1M output tokens
How Much VRAM Does EuroLLM 9B Instruct 2512 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.5 GB | 9.8 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~144 tok/s | |
| 5.1 GB | 10.4 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~128 tok/s | |
| 6.1 GB | 11.4 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~107 tok/s | |
| 7.2 GB | 12.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~91 tok/s | |
| 8.2 GB | 13.5 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~80 tok/s | |
| 9.8 GB | 15.1 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~67 tok/s | |
| 19.0 GB | 24.2 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 16K context · ~35 tok/s |
Selected Q4_K_M
4-bit medium quantization8.6GBat 16K context
- Weights
- 5.5 GB
- KV cache
- 2.8 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 15.4 GB free · ~107 tok/s
≥50 tok/s needs ≥472 GB/s · RTX 5090 ~190, RTX 3090 Ti ~107
Which Hardware Can Run EuroLLM 9B Instruct 2512?
Q4_K_M · 6.1 GBEuroLLM 9B Instruct 2512 (Q4_K_M) requires 6.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. Using the full 33K context window can add up to 5.3 GB, bringing total usage to 11.4 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run EuroLLM 9B Instruct 2512, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
12 GB
12 GB tier →fits · 3.4 GB free · up to 32K ctx
10 GPUs · 1 device family
RTX 3080 Ti~97Simulate output on RTX 3080 TiRTX 5070~71Simulate output on RTX 5070RTX 4070~53Simulate output on RTX 4070iPhone~9Simulate output on Apple iPhone 17 Pro20 GB
fits · 11.4 GB free · up to 32K ctx
1 GPU
RX 7900 XT~78Simulate output on RX 7900 XT32–40 GB
fits · 23.4 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~190Simulate output on RTX 5090M5 Max36 GB~52Simulate output on Mac Studio M5 Max (36 GB)M532 GB~18Simulate output on MacBook Air 13" M5 (32 GB)Orin~22Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~14Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.5 9BAlibaba | 99.4 | 6.6 GB | ~103 | same size |
| Granite Switch 4.1 8BIBM | — | 8.4 GB | ~111 | same size |
| Ornith 1.5 9Bornith-ai | — | 6.6 GB | ~103 | same size |
| Apertus V1.5 8Bswiss-ai | — | 8.5 GB | ~111 | same size |
| MiniCPM O 4 5OpenBMB | — | 8.3 GB | ~105 | same size |
| Qwen3 VL 8B InstructAlibaba | — | 8 GB | ~112 | same size |
Specifications
- Publisher
- utter-project
- Parameters
- 9.2B
- Architecture
- LlamaForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2026-01-26
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does EuroLLM 9B Instruct 2512 need?
EuroLLM 9B Instruct 2512 requires 6.1 GB of VRAM at Q4_K_M, or 19.0 GB at BF16. Full 33K context adds up to 5.3 GB (11.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 9.2B × 4.8 bits ÷ 8 = 5.5 GB
KV Cache + Overhead ≈ 0.6 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 ≈ 5.9 GB (at full 33K context)
VRAM usage by quantization
What's the best quantization for EuroLLM 9B Instruct 2512?
For EuroLLM 9B Instruct 2512, Q4_K_M (6.1 GB) offers the best balance of quality and VRAM usage. Q5_K_M (7.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run EuroLLM 9B Instruct 2512 on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run EuroLLM 9B Instruct 2512. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 6.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run EuroLLM 9B Instruct 2512 locally?
Yes — EuroLLM 9B Instruct 2512 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is EuroLLM 9B Instruct 2512?
At Q4_K_M, EuroLLM 9B Instruct 2512 can reach ~782 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~107 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 ÷ 6.14 × 0.65 = ~847 tok/s
Estimated speed at Q4_K_M (6.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of EuroLLM 9B Instruct 2512?
At Q4_K_M, the download is about 5.49 GB. The full-precision BF16 version is 18.30 GB. The smallest option (Q2_K) is 3.89 GB.
Which GPUs can run EuroLLM 9B Instruct 2512?
52 consumer GPUs can run EuroLLM 9B Instruct 2512 at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run EuroLLM 9B Instruct 2512?
151 devices with unified memory can run EuroLLM 9B Instruct 2512 at Q4_K_M (6.1 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.