Clef — Hardware Requirements & GPU Compatibility
VisionFunctionsClef is Cloudflare's 27-billion-parameter multimodal decision model, post-trained from Qwen3.8-27B. Unlike chat models that output free-form text, it reads a state provided as text, JSON, images, or video alongside a schema of typed questions, then returns probabilities for every allowed option in one forward pass through its small joint schema head. This approach suits classification, routing, and structured decisions well. According to the card, it was tested on a single H200; at this scale it fits on one high-memory GPU when quantized, though the custom head requires the repository's own code. The context length reaches 262,144 tokens. Clef is released under the Apache 2.0 license, which allows unrestricted commercial and research use. Published in September 2026, it also has a smaller sibling named Clef-Flash, built on a 9B Qwen3.5 backbone.
Runs well on a 24 GB GPU
Runs from 12 GB (IQ2_M · 32K)Best on 24 GB (Q4_K_M · ~38 tok/s · 128K)Macs from 16 GB (IQ2_M · ~14 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Clef
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
ollama run hf.co/ggml-org/Clef-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 6.4 GB free · 16K context
Download: Clef-Q4_K_M.gguf19.54 GBggml-org
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3090 (24 GB) (6 GB headroom) · Q4_K_M
- Generation speed
- ~36 tok/s
- generation speed
- Cost per 1M output tokens
- $1.53
- per 1M output tokens
How Much VRAM Does Clef Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 12.4 GB | 13.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~53 tok/s | |
| 12.7 GB | 14.1 GB | 3-bit small — 3-bit small quantization | Fits: 128K context · ~52 tok/s | |
| 14.1 GB | 15.4 GB | 3-bit medium — 3-bit medium quantization | Fits: 128K context · ~47 tok/s | |
| 14.4 GB | 15.8 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 128K context · ~45 tok/s | |
| 17.2 GB | 18.5 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 128K context · ~38 tok/s | |
| 20.2 GB | 21.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 64K context · ~32 tok/s | |
| 23.3 GB | 24.7 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 16K context · ~28 tok/s | |
| 28.1 GB | 29.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 28.6 GB |
Selected Q4_K_M
4-bit medium quantization17.6GBat 16K context
- Weights
- 16.4 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Clef?
Q4_K_M · 17.2 GBClef (Q4_K_M) requires 17.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 23+ GB is recommended. Using the full 262K context window can add up to 13.9 GB, bringing total usage to 31.0 GB. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 137 devices with unified memory can run Clef, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 2.4 GB free · up to 32K ctx
1 GPU
RX 7900 XT~28Simulate output on RX 7900 XT32–40 GB
fits · 14.4 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~68Simulate output on RTX 5090M5 Max*36 GB~19Simulate output on Mac Studio M5 Max (36 GB)M632 GB~7Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~11Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~8Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Qwen3.8 27BAlibaba | 121.9 | 17.9 GB | ~38 | same size |
| Qwen3.6 27BAlibaba | 111.2 | 17.9 GB | ~38 | same size |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | same size |
| Gemma 3 27B ITGoogle | 79.4 | 21.7 GB | ~36 | same size |
| Gemma 4 26B A4BGoogle | — | 16.5 GB | ~171 | same size |
| ERNIE 4.5 VL 28B A3B PTBaidu | — | 60 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- Cloudflare
- Parameters
- 27.4B
- Architecture
- Qwen3_5ForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-09-30
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Clef need?
Clef requires 17.2 GB of VRAM at Q4_K_M, or 55.5 GB at BF16. Full 262K context adds up to 13.9 GB (31.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 27.4B × 4.8 bits ÷ 8 = 16.4 GB
KV Cache + Overhead ≈ 0.8 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 ≈ 14.6 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Clef?
Yes, at Q6_K (23.3 GB) or lower. Higher quantizations like Q8_0 (28.1 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Clef?
For Clef, Q4_K_M (17.2 GB) offers the best balance of quality and VRAM usage. Q4_K_L (17.5 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 10.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Clef on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run Clef, the smallest at IQ2_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 17.2 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Clef locally?
Yes — Clef can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Clef?
At Q4_K_M, Clef can reach ~280 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~38 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 ÷ 17.16 × 0.65 = ~303 tok/s
Estimated speed at Q4_K_M (17.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Clef?
At Q4_K_M, the download is about 16.41 GB. The full-precision BF16 version is 54.71 GB. The smallest option (IQ2_M) is 9.23 GB.
Which GPUs can run Clef?
8 consumer GPUs can run Clef at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Clef?
137 devices with unified memory can run Clef at Q4_K_M (17.2 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.