Model: Metis-1.6 Praxis

Lernex released Metis-1.6 Praxis, the smaller of its two Metis-1.6 models, on 1 November under Apache 2.0, and llama.cpp has run it since 3 November. Metis-1.6 Praxis is a 2.95B-parameter looped hybrid of 12 layers — mostly Mamba-2 with two attention layers and a small mixture-of-experts block on every layer — that runs its stack twice per token, so each token reads about 1.1B parameters' worth of weights and keeps about 8 KB of attention cache per token across a 128K window. Lernex's GGUF files range from 1.84 GB (IQ4_XS) to 3.22 GB (Q8_0), with Q4_K_M needing about 2.2 GB of VRAM at 4K context and 3.2 GB at 128K, and no per-level quality loss has been published.

Metis-1.6 Praxis 3B MoE Metis The smaller of Lernex's two Metis-1.6 models, released on 1 November under Apache 2.0. It is a looped hybrid: 12 layers, mostly Mamba-2 with two attention layers and a small mixture-of-experts block on every layer, and the whole stack runs twice per token, so each token reads about 1.1B parameters' worth of weights from a 2.95B model. Each pass keeps its own attention cache, about 8 KB per token in total, which makes its 128K window cheap. At Q4 K M it needs about 2.2 GB at 4K and 3.2 GB at 128K, comfortable on a 4 GB card. Q8 0 needs about 4.5 GB at 128K, comfortable on a 6 GB card. llama.cpp runs it since 3 November. Sizes come from Lernex's own GGUF files, and no per-level quality loss has been published. 131K Max Context 5 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 | IQ4 XS | 4.98 | 1.9 GB | — | — | Estimated | | | GGUF | Q4 K M | 5.48 | 2.1 GB | — | — | Estimated | | | GGUF | Q5 K M | 6.31 | 2.5 GB | — | — | Estimated | | | GGUF | Q6 K | 7.04 | 2.8 GB | — | — | Estimated | | | GGUF | Q8 0 | 8.74 | 3.4 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 IQ4 XS Lernex/Metis-1.6-Praxis-GGUF https://huggingface.co/Lernex/Metis-1.6-Praxis-GGUF · Metis-1.6-Praxis-IQ4 XS.gguf · 1.84 GB 1,836,154,464 bytes · listing read 2026-11-04 - GGUF Q4 K M Lernex/Metis-1.6-Praxis-GGUF https://huggingface.co/Lernex/Metis-1.6-Praxis-GGUF · Metis-1.6-Praxis-Q4 K M.gguf · 2.02 GB 2,019,139,168 bytes · listing read 2026-11-04 - GGUF Q5 K M Lernex/Metis-1.6-Praxis-GGUF https://huggingface.co/Lernex/Metis-1.6-Praxis-GGUF · Metis-1.6-Praxis-Q5 K M.gguf · 2.33 GB 2,325,706,336 bytes · listing read 2026-11-04 - GGUF Q6 K Lernex/Metis-1.6-Praxis-GGUF https://huggingface.co/Lernex/Metis-1.6-Praxis-GGUF · Metis-1.6-Praxis-Q6 K.gguf · 2.60 GB 2,597,131,872 bytes · listing read 2026-11-04 - GGUF Q8 0 Lernex/Metis-1.6-Praxis-GGUF https://huggingface.co/Lernex/Metis-1.6-Praxis-GGUF · Metis-1.6-Praxis-Q8 0.gguf · 3.22 GB 3,224,393,312 bytes · listing read 2026-11-04 Similar models Compare with Metis-1.6 Logos https://quantized.uk/tools/compare/?a=metis-1-6-praxis&b=metis-1-6-logos 10B MoEConsumer GPUMac / Apple SiliconQ4 K M7.1 GB—perplexity rise https://quantized.uk/quant-hub/metis-1-6-logos/ Metis-1.6 Logos Metis The larger of Lernex's two Metis-1.6 models, released on 1 November under Apache 2.0. It is a looped hybrid: 20 layers, mostly Mamba-2 with three attention layers and a mixture-of-experts block on every layer, and the whole stack runs twice per token, so each token reads about 2.6B parameters' worth of weights from a 10.24B model. Each pass keeps its own attention cache, about 15 KB per token in total. IQ4 XS needs about 6.4 GB at 4K and 6.9 GB at 32K, comfortable on an 8 GB card. Q4 K M needs about 7.1 GB at 4K, tight on an 8 GB card and comfortable from 10 GB up; at 128K it needs about 9.1 GB, comfortable on a 12 GB card. Q8 0 needs about 11.7 GB at 4K, comfortable on a 16 GB card. llama.cpp runs it since 3 November. Sizes come from Lernex's own GGUF files, and no per-level quality loss has been published. 3BConsumer GPUMac / Apple SiliconQ4 K M2.5 GB+3.5%perplexity rise https://quantized.uk/quant-hub/llama-3.2-3b/ Llama 3.2 3B Instruct Meta Llama 3.2 Tiny but capable. Runs on 4GB VRAM or 8GB RAM, even on phones via llama.cpp. 3BConsumer GPUMac / Apple SiliconQ4 K M2.1 GB+3.2%perplexity rise https://quantized.uk/quant-hub/qwen2.5-3b/ Qwen2.5 3B Instruct Alibaba Qwen2.5 Tiny Qwen2.5 for edge devices. Runs on 4GB VRAM or Raspberry Pi class hardware. 1BConsumer GPUMac / Apple SiliconQ4 K M0.9 GB+4.2%perplexity rise https://quantized.uk/quant-hub/llama-3.2-1b/ Llama 3.2 1B Instruct Meta Llama 3.2 Ultra-light Llama for mobile and embedded. Sub-2GB VRAM with Q4. Running Metis-1.6 Praxis locally At Q4 K M and 4K of context, Metis-1.6 Praxis needs about 2.1 GB — 1.9 GB of weights, 0.03 GB of KV cache and a 0.2 GB activation buffer. The smallest cards in this index that clear that comfortably are 8 GB ones — 11 of them, from the Mac M1 8G up — and 78 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 0.22 GB, taking the total to 2.4 GB. That is gentler than the parameter count suggests: only 4 of 12 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 128K; holding all of it at Q4 K M would need about 3 GB. Which build to download This index only tracks Metis-1.6 Praxis in GGUF, across 5 levels IQ4 XS, Q4 K M, Q5 K M, Q6 K, 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 Metis-1.6 Praxis need? - About 2.1 GB at Q4 K M with 4K of context and batch 1, rising to roughly 2.4 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 Metis-1.6 Praxis run on a 8GB GPU? - Yes — at Q4 K M and 4K context it needs about 2.1 GB, which leaves 3.9 GB spare on a Mac M1 8G, or on any of the other 8 GB cards here 11 in all . That is the smallest size in this index that clears it comfortably; 78 of 78 do. - Which quantization of Metis-1.6 Praxis 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 5 levels in the index are IQ4 XS, Q4 K M, Q5 K M, Q6 K, Q8 0. Note this is a mixture-of-experts model — all parameters must be resident even though only a fraction are active per token, so the memory cost follows the total, not the active count. 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 - Mac M1 8G8GB · +3.9 https://quantized.uk/gpu/mac-m1-8g/ Mac M3 8G8GB · +3.9 https://quantized.uk/gpu/mac-m3-8g/ RTX 40608GB · +5.9 https://quantized.uk/gpu/rtx-4060/ RTX 4060 Ti 8G8GB · +5.9 https://quantized.uk/gpu/rtx-4060-ti-8g/ Radeon RX 9060 XT 8G8GB · +5.9 https://quantized.uk/gpu/radeon-rx-9060-xt-8g/ - Ships in - GGUF https://quantized.uk/formats/gguf/ - Try it yourself - Size it in the calculator https://quantized.uk/tools/vram-calc/?model=metis-1-6-praxis&quant=Q4 K M Generate the run command https://quantized.uk/tools/cli-gen/?model=metis-1-6-praxis&quant=Q4 K M 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 2026-11-05 RSS → /feed.xml https://quantized.uk/feed.xml