North Mini Code 1.0 30B-A3B
30B-A3BCohere 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
Similar models
Compare with Seed-OSS 36BSeed-OSS 36B Instruct
ByteDance Seed
Dense 36B with a native 512K context. Q4 weights are ~22GB, which lands on a 24GB card or a 2×16GB split — but the context is the real cost: 512K of KV cache is roughly 128GB on its own, so budget context first and weights second.
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.
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.
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 that is about 17 GB at 32K: comfortable on a 24 GB card, which can still load the whole window (tight). A 16 GB card is just too small. Sizes use the calculator's generic rates — no GGUF file size could be checked, and 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 · +4.0Radeon RX 7900 XTX24GB · +4.0RTX 409024GB · +4.0Tesla P40 24G24GB · +4.0Mac M5 32G32GB · +4.0
- Tight but possible
- Radeon RX 7900 XT20GB
- Ships in
- GGUF
- Try it yourself
- Size it in the calculatorGenerate the run command
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 2026-10-20 RSS → /feed.xml