Command R 35B

35B

Cohere

Cohere's RAG-optimised model. Excellent retrieval-augmented generation.

Pro GPU

131K

Max Context

2

Quant Variants

GGUF Q4_K_M

Best Quality

97.0%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = site benchmarks · Estimated = formula · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.8522.8 GB3.0%42 tok/sEstimated
CalcHF
GPTQINT4420.5 GB4.5%55 tok/sEstimated
CalcHF

Similar models

Compare with Qwen2.5 32B
32B

Qwen2.5 32B Instruct

Alibaba Qwen2.5

Consumer GPUPro GPU
16.4 GBmin VRAM·97.3%accuracy

Near-GPT-4 reasoning on a 24GB VRAM card (Q4_K_S). Groundbreaking value.

24B

Mistral Small 24B Instruct

Mistral AI

Consumer GPUPro GPU
13.5 GBmin VRAM·97.8%accuracy

Mistral's efficient 24B. Strong multilingual; fits on 24GB with Q4.

34B

Yi 1.5 34B Chat

01.AI Yi

Consumer GPUPro GPU
19.8 GBmin VRAM·97.2%accuracy

01.AI's strong bilingual (EN/ZH) model. Competitive with Qwen 32B.

27B

Gemma 2 27B Instruct

Google Gemma 2

Consumer GPUPro GPU
16.2 GBmin VRAM·98.7%accuracy

Largest open Gemma 2. Strong reasoning; needs 24GB+ VRAM at Q4.