Clef Flash — Hardware Requirements & GPU Compatibility
VisionFunctionsClef-Flash is Cloudflare's 9-billion-parameter multimodal decision model, post-trained from Qwen3.5-9B. It does not generate free-form text. It takes a state as text, JSON, images or video together with a schema of typed questions, and outputs a probability for each allowed option in one forward pass, using a small joint schema head on the backbone's hidden states. It is meant for classification, routing and other structured decisions, and the card describes it as the smaller, faster variant of Clef. At this size it fits on a single consumer GPU once quantized, although the custom head requires the repository's own loading code. The context length is 262,144 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. Published in September 2026, it is the smaller companion to the 27B Clef model.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~106 tok/s · 256K)Macs from 8 GB (IQ3_XXS · ~17 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Clef Flash
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-Flash-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 17.5 GB free · 16K context
Download: Clef-Flash-Q4_K_M.gguf6.73 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 3080 (10 GB) (3 GB headroom) · Q4_K_M
- Generation speed
- ~80 tok/s
- generation speed
- Cost per 1M output tokens
- $0.42
- per 1M output tokens
How Much VRAM Does Clef Flash Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.6 GB | 5.4 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~143 tok/s | |
| 4.7 GB | 5.5 GB | 3-bit small — 3-bit small quantization | Fits: 256K context · ~140 tok/s | |
| 5.2 GB | 6 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~127 tok/s | |
| 5.3 GB | 6.1 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 256K context · ~124 tok/s | |
| 6.2 GB | 7 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~106 tok/s | |
| 7.3 GB | 8.1 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~90 tok/s | |
| 8.3 GB | 9.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~79 tok/s | |
| 10.0 GB | 10.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~66 tok/s |
Selected Q4_K_M
4-bit medium quantization6.5GBat 16K context
- Weights
- 5.6 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Clef Flash?
Q4_K_M · 6.2 GBClef Flash (Q4_K_M) requires 6.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 9+ GB is recommended. Using the full 262K context window can add up to 8.3 GB, bringing total usage to 14.5 GB. 95 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 172 devices with unified memory can run Clef Flash, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), NVIDIA Jetson Orin Nano 8GB (Super).
12 GB
12 GB tier →fits · 5.5 GB free · up to 128K ctx
16 GPUs · 1 device family
RTX 3080 12GB~96Simulate output on RTX 3080 12GBRTX 3080 Ti~96Simulate output on RTX 3080 TiRTX 5070~70Simulate output on RTX 5070iPhone~9Simulate output on Apple iPhone 17 Pro20 GB
fits · 13.5 GB free · up to 256K ctx
1 GPU
RX 7900 XT~77Simulate output on RX 7900 XT32–40 GB
fits · 25.5 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~188Simulate output on RTX 5090M5 Max*36 GB~52Simulate output on Mac Studio M5 Max (36 GB)M632 GB~19Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~32Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~21Simulate 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 |
|---|---|---|---|---|
| Qwen3.5 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
- Cloudflare
- Parameters
- 9.4B
- 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 Flash need?
Clef Flash requires 6.2 GB of VRAM at Q4_K_M, or 19.4 GB at BF16. Full 262K context adds up to 8.3 GB (14.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 9.4B × 4.8 bits ÷ 8 = 5.6 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 ≈ 8.9 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for Clef Flash?
For Clef Flash, Q4_K_M (6.2 GB) offers the best balance of quality and VRAM usage. Q4_K_L (6.3 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 3.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Clef Flash on a Mac?
Yes — Mac Mini M2 (8 GB) and 158 other Macs can run Clef Flash, 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 6.2 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run Clef Flash locally?
Yes — Clef Flash can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Clef Flash?
At Q4_K_M, Clef Flash can reach ~773 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~106 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 ÷ 6.21 × 0.65 = ~837 tok/s
Estimated speed at Q4_K_M (6.2 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Clef Flash?
At Q4_K_M, the download is about 5.65 GB. The full-precision BF16 version is 18.82 GB. The smallest option (IQ2_XXS) is 2.59 GB.
Which GPUs can run Clef Flash?
95 consumer GPUs can run Clef Flash at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6700M, AMD Radeon RX 6750 XT, AMD Radeon RX 5700 XT. 51 GPUs have plenty of headroom for comfortable inference.
Which devices can run Clef Flash?
172 devices with unified memory can run Clef Flash at Q4_K_M (6.2 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.