Model: North Mini Code 1.0 30B-A3B

Cohere released North Mini Code 1.0 30B-A3B in June, an open text-only coding model built as a 30B mixture-of-experts with about 3B parameters active per token for code generation, agentic software work and terminal tasks. Only 13 of its 49 layers keep a context-growing cache, so the Q4_K_M GGUF file (18.7 GB) needs about 20.0 GB of VRAM at 4K context, 20.8 GB at 32K and 23.5 GB at 128K, fitting a 24 GB card comfortably to 32K and tightly at 128K, while a 16 GB card requires Q3_K_M (14.2 GB) at about 15.3 GB at 4K. The model card lists 256K context while its config allows 500K, and no per-quantization quality loss has been published; Cohere's benchmark claims are its own.

North Mini Code 1.0 30B-A3B 30B-A3B Cohere North Cohere's open coding model, released in June: a 30B mixture-of-experts with about 3B parameters active per token. It is built for code generation, agentic software work and terminal tasks, and takes text only. Only 13 of its 49 layers keep a cache that grows with context, so long sessions stay affordable: at Q4 K M bartowski's 18.7 GB file it needs about 20.0 GB at 4K, 20.8 GB at 32K and 23.5 GB at 128K — comfortable on a 24 GB card up to 32K and tight at 128K. A 16 GB card needs Q3 K M bartowski's 14.2 GB file : about 15.3 GB at 4K, tight, and too big past 32K. The model card says 256K context while its config allows 500K; this page uses 256K. Sizes come from the published GGUF files; no per-level quality loss has been published, and Cohere's benchmark claims are its own. 262K Max Context 3 Quant Variants GGUF Q8 0 Best Quality — Accuracy Retained 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 | 3.73 | 14.2 GB | — | — | Estimated | | | GGUF | Q4 K M | 4.92 | 18.7 GB | — | — | Estimated | | | GGUF | Q8 0 | 8.51 | 32.4 GB | — | — | Estimated | | Which file each size is for A file size is not a memory figure: the VRAM column adds the KV cache at 4K context and runtime buffers to the weights. A vision projector mmproj , where the repo ships one, is a separate download and is in neither number. - GGUF Q3 K M bartowski/North-Mini-Code-1.0-GGUF https://huggingface.co/bartowski/North-Mini-Code-1.0-GGUF · file name not recorded · 14.21 GB 14,209,048,128 bytes · listing read 2026-10-20 - GGUF Q4 K M bartowski/North-Mini-Code-1.0-GGUF https://huggingface.co/bartowski/North-Mini-Code-1.0-GGUF · file name not recorded · 18.74 GB 18,744,024,640 bytes · listing read 2026-10-20 - GGUF Q8 0 bartowski/North-Mini-Code-1.0-GGUF https://huggingface.co/bartowski/North-Mini-Code-1.0-GGUF · file name not recorded · 32.44 GB 32,437,263,936 bytes · listing read 2026-10-20 Similar models Compare with Seed-OSS 36B https://quantized.uk/tools/compare/?a=north-mini-code-1.0&b=seed-oss-36b 36BConsumer GPUPro GPU19.5 GBmin VRAM98.7%accuracy https://quantized.uk/quant-hub/seed-oss-36b/ Seed-OSS 36B Instruct ByteDance Seed Dense 36B with a native 512K context. The Q4 K M file is 21.8 GB, so with cache and buffers it needs about 23.9 GB at 4K: tight on a 24 GB card, where Q3 K M 19.5 GB is the comfortable choice, or a 2×16GB split. The AWQ build is 21.1 GB, not the 4-bit rate the name suggests. Context is the real cost: 512K of KV cache is roughly 128GB on its own, so budget context first and weights second. 27BConsumer GPUPro GPU15.3 GBmin VRAM—accuracy https://quantized.uk/quant-hub/qwen3-8-27b/ Qwen3.8 27B Alibaba Qwen3.8 Hybrid attention: only 16 of its 64 layers keep a KV cache, which is why a 27B model holds a 262K context in about 16GB of cache rather than 64GB. Sizing it as a conventional stack overstates the cache fourfold — the estimates here count the 16 and match published measurements at 8K, 32K and 262K. Quality loss per level has not been published. 30B-A3BConsumer GPUPro GPU18.2 GBmin VRAM—accuracy https://quantized.uk/quant-hub/glm-4.7-flash/ GLM-4.7-Flash Zhipu GLM-4.7 Zhipu's lightweight member of GLM-4.7: 30B total, about 3B active per token, MIT licence. Its attention is MLA, which caches one compressed 576-value vector per token per layer instead of full keys and values — so at 32K context the cache is under 2 GB where a conventional 47-layer model would need several times that. llama.cpp runs it as a DeepSeek-2-style model. Sizes below use the calculator's generic Q4 K M/Q8 0 rates: no GGUF file size could be checked, and quality loss per level has not been published. 26B-A4BConsumer GPUPro GPU15.3 GBmin VRAM—accuracy 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. Running North Mini Code 1.0 30B-A3B locally At Q4 K M and 4K of context, North Mini Code 1.0 30B-A3B needs about 20.0 GB — 17.8 GB of weights, 0.38 GB of KV cache and a 1.8 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 0.75 GB, taking the total to 20.8 GB. That is gentler than the parameter count suggests: only 13 of 49 layers keep a KV cache that grows with context, and 36 more cap theirs at a sliding window, 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 27 GB. Which build to download This index only tracks North Mini Code 1.0 30B-A3B in GGUF, across 3 levels Q3 K M, Q4 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 North Mini Code 1.0 30B-A3B need? - About 20.0 GB at Q4 K M with 4K of context and batch 1, rising to roughly 20.8 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 North Mini Code 1.0 30B-A3B run on a 24GB GPU? - Yes — at Q4 K M and 4K context it needs about 20.0 GB, which leaves 4.0 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 North Mini Code 1.0 30B-A3B 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 3 levels in the index are Q3 K M, Q4 K M, 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 - RTX 309024GB · +4.0 https://quantized.uk/gpu/rtx-3090/ Radeon RX 7900 XTX24GB · +4.0 https://quantized.uk/gpu/radeon-rx-7900-xtx/ RTX 409024GB · +4.0 https://quantized.uk/gpu/rtx-4090/ Tesla P40 24G24GB · +4.0 https://quantized.uk/gpu/tesla-p40-24g/ Mac M5 32G32GB · +4.0 https://quantized.uk/gpu/mac-m5-32g/ - Tight but possible - Radeon RX 7900 XT20GB https://quantized.uk/gpu/radeon-rx-7900-xt/ - Ships in - GGUF https://quantized.uk/formats/gguf/ - Try it yourself - Size it in the calculator https://quantized.uk/tools/vram-calc/?model=north-mini-code-1.0&quant=Q4 K M Generate the run command https://quantized.uk/tools/cli-gen/?model=north-mini-code-1.0&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 2026-10-23 RSS → /feed.xml https://quantized.uk/feed.xml