Command R 35B
35BCohere
⚠ Superseded · Prefer Qwen3.8 27B
This index would suggest Qwen3.8 27B instead today — longer context (128K → 256K tokens). The numbers below are still accurate; they are just for a model you probably should not start with. Compare the two →
Cohere's RAG-optimised model. Excellent retrieval-augmented generation.
131K
Max Context
2
Quant Variants
GGUF Q4_K_M
Best Quality
97.0%
Accuracy Retained
Quantization Variants
Per-quant VRAM, quality loss, and inference speed on RTX 4090
Measured = site benchmarks · Estimated = formula · Community = public reports
Similar models
Compare with Qwen2.5 32BQwen2.5 32B Instruct
Alibaba Qwen2.5
Near-GPT-4 reasoning on a 24GB VRAM card (Q4_K_S). Groundbreaking value.
Mistral Small 24B Instruct
Mistral AI
Mistral's efficient 24B. Strong multilingual; fits on 24GB with Q4.
Yi 1.5 34B Chat
01.AI Yi
01.AI's strong bilingual (EN/ZH) model. Competitive with Qwen 32B.
Gemma 2 27B Instruct
Google Gemma 2
Largest open Gemma 2. Strong reasoning; needs 24GB+ VRAM at Q4.
Running Command R 35B locally
At Q4_K_M and 4K of context, Command R 35B needs about 22.9 GB — 20.2 GB of weights, 0.63 GB of KV cache and a 2.1 GB activation buffer. The smallest card in this index that clears that comfortably is the RTX 5090 at 32 GB, and 24 of the 63 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 4.37 GB, taking the total to 27.7 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4_K_M would need about 44 GB.
Which build to download
This index tracks 2 formats for it — GGUF, GPTQ — across 2 levels. Q4_K_M carries the lowest published perplexity loss at 3.0%. The fastest level measured here is GPTQ INT4 at 55 tok/s on an RTX 4090, batch 1. 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 and CUDA only.
Common questions
- How much VRAM does Command R 35B need?
- About 22.9 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 27.7 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 Command R 35B run on a 32GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 22.9 GB, which leaves 9.1 GB spare on a RTX 5090. That is the smallest card in this index that clears it comfortably; 24 of 63 do.
- Which quantization of Command R 35B should I use?
- Q4_K_M has the lowest published quality loss (3.0%), and Q4_K_M is the level most people run. All 2 levels in the index are Q4_K_M, GPTQ INT4.
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 509032GB · +9.1Instinct MI100 32G32GB · +9.1Mac M4 Max 36G36GB · +4.1Mac M3 Pro 36G36GB · +4.1A100 40G40GB · +17.1
- Tight but possible
- RTX 409024GBRTX 309024GBTesla P40 24G24GB
- Compared here
- GGUF vs GPTQ
- 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 2026-09-21 RSS → /feed.xml