27B Nous Research Arete
Nous Research post-trained Qwen3.8 27B for general assistance and agentic use without changing its architecture. Only 16 of 64 layers grow a KV cache. Memory is estimated from bartowski GGUF files; the separate vision projector is optional and its bytes are recorded. Quantization quality loss and speed for these files have not been verified.
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 | 3.849895205159721 | 14.0 GB | — | — | Estimated | |
| GGUF | Q4_K_M | 5.030840153644453 | 18.3 GB | — | — | Estimated | |
| GGUF | Q5_K_M | 6.048937653823034 | 21.9 GB | — | — | Estimated | |
| GGUF | Q8_0 | 8.382601298581587 | 30.2 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_Mbartowski/NousResearch_Arete-27B-GGUF · NousResearch_Arete-27B-Q3_K_M.gguf · 13.17 GB (13,165,067,264 bytes) · + vision projector 0.93 GB, separate · listing read 2026-11-15
- GGUF Q4_K_Mbartowski/NousResearch_Arete-27B-GGUF · NousResearch_Arete-27B-Q4_K_M.gguf · 17.20 GB (17,203,416,064 bytes) · + vision projector 0.93 GB, separate · listing read 2026-11-15
- GGUF Q5_K_Mbartowski/NousResearch_Arete-27B-GGUF · NousResearch_Arete-27B-Q5_K_M.gguf · 20.68 GB (20,684,893,184 bytes) · + vision projector 0.93 GB, separate · listing read 2026-11-15
- GGUF Q8_0bartowski/NousResearch_Arete-27B-GGUF · NousResearch_Arete-27B-Q8_0.gguf · 28.67 GB (28,665,068,544 bytes) · + vision projector 0.93 GB, separate · listing read 2026-11-15
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 Gemma 4](https://quantized.uk/tools/compare/?a=arete-27b&b=gemma-4-26b-a4b)
[26B-A4BConsumer GPUPro GPUQ4_K_M18.2 GB—perplexity rise](https://quantized.uk/quant-hub/gemma-4-26b-a4b/)
Gemma 4 26B-A4B IT
Google Gemma 4
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.
31BConsumer GPUPro GPUQ4_K_M22.1 GB—perplexity rise
Gemma 4 31B IT
Google Gemma 4
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.
35B-A3BConsumer GPUPro GPUQ4_K_M23.4 GB—perplexity rise
Qwen3.6 35B-A3B
Alibaba Qwen3.6
One of the most recommended models for a 24 GB card this year: 35.5B parameters, about 3B active per token, so it reads per token about as much as a 3B model. Only 10 of its 40 layers keep a growing KV cache, so context is cheap: at Q4_K_M it needs about 23.4 GB at 4K and 24.0 GB at 32K. On this site's rule that is tight on a 24 GB card, not comfortable, because it counts a working buffer most guides leave out. A 32 GB card, or a 48 GB Mac through the GPU's share of unified memory, has real room. It reads images through a separate vision encoder. Sizes come from bartowski's GGUF files; Unsloth's UD-Q4_K_M is a different file, 0.15 GB smaller. No per-level quality loss has been published.
27BConsumer GPUPro GPUQ4_K_M19.1 GB—perplexity rise
Qwen3.6 27B
Alibaba Qwen3.6
The dense model of the Qwen3.6 generation and a popular local coding model. It has the same layout as Qwen3.8 27B, the newer release: only 16 of its 64 layers keep a growing KV cache. At Q4_K_M it needs about 19.1 GB at 4K context and 21.0 GB at 32K, comfortable on a 24 GB card either way. Q5_K_M is tight on 24 GB, and a 16 GB card cannot hold it at any level listed here. Sizes come from bartowski's published GGUF files; Unsloth's builds of the same levels are about 1 GB smaller. No per-level quality loss has been published.
Running Arete 27B locally #
At Q4_K_M and 4K of context, Arete 27B needs about 18.3 GB — 16.3 GB of weights, 0.25 GB of KV cache and a 1.7 GB activation buffer. The smallest cards in this index that clear that comfortably are 24 GB ones — 4 of them, from the RTX 3090 up — and 31 of the 78 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 20.2 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 36 GB.
Which build to download #
This index only tracks Arete 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 Arete 27B need?
- About 18.3 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 20.2 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 Arete 27B run on a 24GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 18.3 GB, which leaves 5.8 GB spare on a RTX 3090, or on any of the other 24 GB cards here (4 in all). That is the smallest size in this index that clears it comfortably; 31 of 78 do.
- Which quantization of Arete 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.
-
Runs comfortably on
-
RTX 309024GB · +5.8Radeon RX 7900 XTX24GB · +5.8RTX 409024GB · +5.8Tesla P40 24G24GB · +5.8Mac M5 32G32GB · +5.8
-
Tight but possible
-
Ships in
-
A top pick for
-
Try it yourself
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 2026-11-15 RSS → /feed.xml