Skip to content

Clairic 27B

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.

⬇ 1.4K HF downloads♥ 0 likesXylolabs/clairic-GGUF· stats from 11/22/2026
Consumer GPUPro GPUMac / Apple Silicon

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

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ3_K_M4.02941458823545514.4 GB——Estimated
CalcHF
GGUFQ4_K_M4.98987303689935217.8 GB——Estimated
CalcHF
GGUFQ5_K_M5.75917059421795120.5 GB——Estimated
CalcHF
GGUFQ8_08.51215904887999430.2 GB——Estimated
CalcHF

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-GGUF · clairic-Q3_K_M.gguf · 13.55 GB (13,546,891,072 bytes) · + vision projector 0.93 GB, separate · listing read 2026-11-21
  • GGUF Q4_K_MXylolabs/clairic-GGUF · clairic-Q4_K_M.gguf · 16.78 GB (16,775,952,192 bytes) · + vision projector 0.93 GB, separate · listing read 2026-11-21
  • GGUF Q5_K_MXylolabs/clairic-GGUF · clairic-Q5_K_M.gguf · 19.36 GB (19,362,330,432 bytes) · + vision projector 0.93 GB, separate · listing read 2026-11-21
  • GGUF Q8_0Xylolabs/clairic-GGUF · clairic-Q8_0.gguf · 28.62 GB (28,617,877,088 bytes) · + vision projector 0.93 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 ↗
9B

Clairic Flash 9B

Cloudflare Clairic

Consumer GPUPro GPU
Q4_K_M6.1 GB—perplexity rise

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.

30B-A3B

Qwen3-VL 30B-A3B Instruct

Alibaba Qwen3-VL

Consumer GPUPro GPU
Q4_K_M19.9 GB+2.6%perplexity rise

Multimodal MoE with only ~3B active parameters, so it stays responsive on Apple unified memory and survives CPU offload far better than a dense 30B. At Q4_K_M it needs about 19.9 GB at 4K, comfortable on a 24 GB card; Q3_K_M brings that to 15.1 GB. The vision encoder is a separate 1.1 GB file.

26B-A4B

Gemma 4 26B-A4B IT

Google Gemma 4

Consumer GPUPro GPU
Q4_K_M18.2 GB—perplexity rise

Google's Gemma 4 mixture-of-experts model: about 25B parameters in the text model, roughly 4B active per token, a 256K window and image input. Only 5 of its 30 layers keep a cache that grows with context, and those use fewer, wider heads, so the cache stays small — about 0.9 GB at 32K and 5.3 GB at the full 256K. At Q4_K_M that is about 18.8 GB at 32K: comfortable on a 24 GB card, which can still load the whole window (tight, about 23.6 GB). A 16 GB card cannot hold it, since the Q4_K_M file alone is 17.0 GB. The vision encoder is a separate 1.2 GB file on top. Sizes come from bartowski's GGUF files, whose Q4_K_M works out at 5.40 bits per weight, well above the generic 4-bit rate; Unsloth's UD-Q4_K_M is a different file, 0.09 GB smaller. No per-level quality loss has been published.

31B

Gemma 4 31B IT

Google Gemma 4

Consumer GPUPro GPU
Q4_K_M22.1 GB—perplexity rise

Google's dense Gemma 4 flagship: about 31B parameters, a 256K window and image input. Only 10 of its 60 layers cache the full context, and those use four wide KV heads, so 128K of context adds about 11 GB of cache where a conventional 60-layer design would need about 120 GB. At Q4_K_M it needs about 22.1 GB at 4K, tight on a 24 GB card; Q3_K_M is about 18.3 GB at 4K. A 32 GB card holds Q4_K_M at 32K comfortably. Google also publishes its own quantization-aware (QAT) Q4_0 build, a single 17.7 GB file: about 20.1 GB at 4K, comfortable on 24 GB up to 16K. Its 1.2 GB vision encoder is a separate file, and with it loaded even 4K is tight on 24 GB. The other levels are sized from bartowski's GGUF files, and no per-level quality loss has been published. That repository also carries two MTP draft-head files (349 MB at Q4_0, 515 MB at Q8_0) for speculative decoding; they are not the model itself and are not counted in these sizes.

Running Clairic 27B locally

At Q4_K_M and 4K of context, Clairic 27B needs about 17.8 GB — 15.9 GB of weights, 0.25 GB of KV cache and a 1.6 GB activation buffer. The smallest cards in this index that clear that comfortably are 24 GB ones — 5 of them, from the RTX 3090 up — and 32 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 1.75 GB, taking the total to 19.7 GB. That is gentler than the parameter count suggests: only 16 of 64 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 35 GB.

Which build to download

This index only tracks Clairic 27B 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 27B need?
About 17.8 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 19.7 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 27B run on a 24GB GPU?
Yes — at Q4_K_M and 4K context it needs about 17.8 GB, which leaves 6.2 GB spare on a RTX 3090, or on any of the other 24 GB cards here (5 in all). That is the smallest size in this index that clears it comfortably; 32 of 105 do.
Which quantization of Clairic 27B 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.

Ships in
GGUF

Cards for this model

This page's figures change when the model or the runtime does.Last updated 2026-11-22 RSS → /feed.xml