llmrun
CloudflareQwen3_5ForConditionalGeneration

Clef Flash — Hardware Requirements & GPU Compatibility

VisionFunctions

Clef-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.

9.4B params · dense262K contextApache 2.036.8K downloads921 likes72.2K quant downloads
Based on Qwen3.5 9B
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 32KBest on24 GB Q4_K_M · ~106 tok/s · 256KMacs from8 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
one command · needs Ollama installed
$ollama run hf.co/ggml-org/Clef-Flash-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 17.5 GB free · 16K context

Download: Clef-Flash-Q4_K_M.gguf6.73 GBggml-org

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run 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

How Much VRAM Does Clef Flash Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
4.6 GB5.4 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 256K context · ~143 tok/s
4.7 GB5.5 GB3-bit small — 3-bit small quantizationFits: 256K context · ~140 tok/s
5.2 GB6 GB3-bit medium — 3-bit medium quantizationFits: 256K context · ~127 tok/s
5.3 GB6.1 GB4-bit · legacy — 4-bit legacy quantizationFits: 256K context · ~124 tok/s
6.2 GB7 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 256K context · ~106 tok/s
7.3 GB8.1 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 256K context · ~90 tok/s
8.3 GB9.1 GB6-bit, very good — 6-bit quantization, very good qualityFits: 256K context · ~79 tok/s
10.0 GB10.8 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 256K context · ~66 tok/s

Selected Q4_K_M

4-bit medium quantization

6.5GBat 16K context

Weights
5.6 GB
KV cache
0.5 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 17.5 GB free · ~106 tok/s

≥50 tok/s needs ≥477 GB/s · RTX 5090 ~188, M5 Ultra ~138

Which Hardware Can Run Clef Flash?

Q4_K_M · 6.2 GB

Clef 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).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 6.5 GB · ~29 tok/s · 32K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 6.5 GB · ~38 tok/s · 128K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 6.5 GB · ~47 tok/s · 256K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 6.5 GB · ~106 tok/s · 256K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 6.5 GB · ~14 tok/s · 256KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 6.5 GB · ~62 tok/s · 256KMacs →

Alternatives to Clef Flash

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Qwen3.5 9BAlibaba99.46.6 GB~103same size
Granite Switch 4.1 8BIBM—8.4 GB~111same size
Ornith 1.5 9Bornith-ai—6.6 GB~103same size
Apertus V1.5 8Bswiss-ai—8.5 GB~111same size
MiniCPM O 4 5OpenBMB—8.3 GB~105same size
Qwen3 VL 8B InstructAlibaba—8 GB~112same 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

6.2 GB
14.5 GB

Learn more about VRAM estimation →

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

IQ2_XXS
3.2 GB
IQ3_S
4.6 GB
Q3_K_L
5.4 GB
Q4_K_M ★
6.2 GB
Q5_0
6.5 GB
BF16
19.4 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

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)

~837 tok/s
~106 tok/s
~837 tok/s
~773 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

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.