Clairic Flash 9B
9BCloudflare Clairic
Cloudflare’s smaller Clairic checkpoint derives from Qwen3.5 9B and handles structured extraction from text and images. The official schema helpers use Transformers and XGrammar. This entry tracks the Xylolabs language GGUF and its separate BF16 projector. Eight of 32 layers grow the main KV cache. No per-quant speed or perplexity loss is recorded.
262K
Max Context
4
Quant Variants
GGUF Q8_0
Best Quality
—
Perplexity rise (best build)
Quantization Variants
Per-quant VRAM, quality loss, and inference speed on RTX 4090
Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports
| Format | Level | BPW | VRAM | PPL Loss | Speed | Source | Actions |
|---|---|---|---|---|---|---|---|
| GGUF | Q3_K_M | 4.191357399920642 | 5.0 GB | — | — | Estimated | |
| GGUF | Q4_K_M | 5.083922583716041 | 6.1 GB | — | — | Estimated | |
| GGUF | Q5_K_M | 5.810236102145387 | 6.9 GB | — | — | Estimated | |
| GGUF | Q8_0 | 8.517853147236629 | 10.1 GB | — | — | Estimated |
Which file each size is for
A file size is not a memory figure: the VRAM column is the calculator's total at 4K context — weights plus KV cache plus a 10% activation buffer. Units differ on purpose: file sizes are decimal GB, as Hugging Face lists them; the VRAM column is GiB (1024³ bytes) with 2% added to the weights, so 7.12 GB of file counts as about 6.8 GiB there. A vision projector (mmproj), where the repo ships one, is a separate download and is in neither number.
- GGUF Q3_K_MXylolabs/clairic-flash-GGUF · clairic-flash-Q3_K_M.gguf · 4.69 GB (4,691,073,696 bytes) · + vision projector 0.92 GB, separate · listing read 2026-11-21
- GGUF Q4_K_MXylolabs/clairic-flash-GGUF · clairic-flash-Q4_K_M.gguf · 5.69 GB (5,690,055,328 bytes) · + vision projector 0.92 GB, separate · listing read 2026-11-21
- GGUF Q5_K_MXylolabs/clairic-flash-GGUF · clairic-flash-Q5_K_M.gguf · 6.50 GB (6,502,963,872 bytes) · + vision projector 0.92 GB, separate · listing read 2026-11-21
- GGUF Q8_0Xylolabs/clairic-flash-GGUF · clairic-flash-Q8_0.gguf · 9.53 GB (9,533,397,664 bytes) · + vision projector 0.92 GB, separate · listing read 2026-11-21
Related community runs
These runs describe their own settings. Their speeds do not replace this estimate or prove your configuration fits.
Our reviewed link index has no run for this model yet. You can browse community reports or share your own test below.
Browse more runs on llamaPerf ↗Similar models
Compare with Clairic 27BClairic 27B
Cloudflare Clairic
Cloudflare’s Qwen3.8 27B derivative produces typed structured outputs from text and images. Its documented schema helpers use Transformers and XGrammar. The indexed Xylolabs GGUF sizes cover the language weights and a separate BF16 projector. The calculator uses the 16 layers that grow the main KV cache. No per-quant speed or perplexity loss is recorded.
Llama 3.2 11B Vision Instruct
Meta Llama 3.2
Multimodal Llama with image understanding. Vision encoder adds ~2GB VRAM overhead.
Gemma 3 12B IT
Google Gemma 3
Mid-size Gemma 3 with vision. Fits 16GB at Q4; excellent multilingual chat.
Qwen3-VL 8B Instruct
Alibaba Qwen3-VL
Current-generation vision-language model that still fits a single 8–12GB card at Q4 (~5.9GB). The realistic multimodal option for people without a 24GB GPU — note the vision encoder adds VRAM the KV-cache math below does not model.
Running Clairic Flash 9B locally
At Q4_K_M and 4K of context, Clairic Flash 9B needs about 6.1 GB — 5.4 GB of weights, 0.13 GB of KV cache and a 0.6 GB activation buffer. The smallest cards in this index that clear that comfortably are 8 GB ones — 21 of them, from the RTX 4060 up — and 98 of the 105 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.
What longer context costs
Going from 4K to 32K adds about 0.87 GB, taking the total to 7.0 GB. That is gentler than the parameter count suggests: only 8 of 32 layers keep a KV cache that grows with context, so the cache scales at a fraction of the usual rate. The model's native window is 256K; holding all of it at Q4_K_M would need about 15 GB.
Which build to download
This index only tracks Clairic Flash 9B in GGUF, across 4 levels (Q3_K_M, Q4_K_M, Q5_K_M, Q8_0). No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.
Common questions
- How much VRAM does Clairic Flash 9B need?
- About 6.1 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 7.0 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
- Will Clairic Flash 9B run on a 8GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 6.1 GB, which leaves 1.9 GB spare on a RTX 4060, or on any of the other 8 GB cards here (21 in all). That is the smallest size in this index that clears it comfortably; 98 of 105 do.
- Which quantization of Clairic Flash 9B should I use?
- No published quality comparison exists for this model, so pick by footprint: Q4_K_M is the level most people run, and a higher bits-per-weight level is more faithful. All 4 levels in the index are Q3_K_M, Q4_K_M, Q5_K_M, Q8_0.
Where this model fits
Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.
- Runs comfortably on
- RTX 40608GB · +1.9RTX 4060 Ti 8G8GB · +1.9Radeon RX 9060 XT 8G8GB · +1.9RTX 5060 Ti 8G8GB · +1.9RTX 50608GB · +1.9
- Tight but possible
- RTX 4050 Laptop GPU6GBRTX 3060 Laptop GPU6GBRTX 3050 Laptop GPU 6G6GB
- Ships in
- GGUF
- Try it yourself
- Size it in the calculatorGenerate the run command
Cards for this model
- RTX 5090
- RTX 5080
- RTX 5070 Ti
- RTX 5070
- RTX 5060 Ti 16G
- RTX 5060 Ti 8G
- RTX 5060
- RTX 4090
- RTX 4080 Super
- RTX 4070 Ti Super
- RTX 4070 Ti
- RTX 4070 Super
- RTX 4070
- RTX 4060 Ti 16G
- RTX 4060 Ti 8G
- RTX 4060
- RTX 3090
- RTX 3080 Ti
- RTX 3080 12G
- RTX 3080 10G
- RTX 3070 Ti
- RTX 3070
- RTX 3060 12G
- A100 40G
- Tesla P100 16G
- Tesla P40 24G
- Mac M5 32G
- Mac M4 Max 36G
- Mac M4 Pro 48G
- Mac M4 Pro 24G
- Mac M3 Max 48G
- Mac M3 Pro 36G
- Mac M3 Pro 18G
- Mac M3 16G
- Mac M3 8G
- Mac M4 24G
- Mac M4 16G
- Mac M2 16G
- Mac M1 16G
- Mac M1 8G
- Radeon RX 9070 XT
- Radeon RX 9070
- Radeon RX 9060 XT 16G
- Radeon RX 9060 XT 8G
- Radeon RX 7900 XTX
- Radeon RX 7900 XT
- Radeon RX 7900 GRE
- Radeon RX 7800 XT
- Radeon RX 7700 XT
- Radeon RX 7600 XT
- Radeon RX 6900 XT
- Radeon RX 6800 XT
- Radeon RX 6700 XT
- Radeon AI PRO R9700 32G
- Instinct MI100 32G
- Arc B580 12G
- Arc B570 10G
- Arc A770 16G
- Arc A750 8G
- Arc Pro B70 32G
- Radeon RX 7800M
How to actually run this
Deployment guides for this model and this class of hardware.
This page's figures change when the model or the runtime does.Last updated 2026-11-22 RSS → /feed.xml