Cohere Command A (111B) — VRAM Requirements, Quantization Matrix & GPU Guide
Cohere Command A (111B) (Cohere, CC-BY-NC-4.0) is a Dense Transformer architecture with 111B resident parameters (111B active per token), 64 layers, and Hybrid Sliding-Window (SWA) supporting up to 262,144 context tokens.
Interactive Cohere Command A (111B) Memory & Context Simulator
Precision & Quantization VRAM Matrix (8K / 32K / 128K Context)
| Precision / Format | Effective bpw | Weights Only | Total @ 8K ctx | Total @ 32K ctx | Total @ 128K ctx | Recommended Tier (@ 32K) |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 bpw | 206.75 GB | 215.85 GB | 217.35 GB | 223.35 GB | Mac Studio 512GB |
| FP8 | 8.50 bpw | 109.84 GB | 116.02 GB | 117.52 GB | 123.52 GB | NVIDIA H200 141GB |
| Q8_0 | 8.50 bpw | 109.84 GB | 116.02 GB | 117.52 GB | 123.52 GB | NVIDIA H200 141GB |
| Q6_K | 6.56 bpw | 84.77 GB | 90.20 GB | 91.70 GB | 97.70 GB | RTX PRO 6000 96GB |
| Q5_K_M | 5.69 bpw | 73.53 GB | 78.62 GB | 80.12 GB | 86.12 GB | RTX PRO 6000 96GB |
| Q4_K_M | 4.85 bpw | 62.67 GB | 67.44 GB | 68.94 GB | 74.94 GB | NVIDIA A100 80GB |
| AWQ INT4 | 4.50 bpw | 58.15 GB | 62.78 GB | 64.28 GB | 70.28 GB | NVIDIA A100 80GB |
| IQ4_XS | 4.25 bpw | 54.92 GB | 59.46 GB | 60.96 GB | 66.96 GB | NVIDIA A100 80GB |
Hardware Compatibility & Decode Speed (Cohere Command A (111B) @ Q4_K_M, 32K Context)
| Hardware Tier | Memory & Bandwidth | Required (32K) | Fit Verdict | Est. Decode Speed |
|---|---|---|---|---|
| RTX 3090 24GB | 24 GB · 936 GB/s | 68.94 GB (287%) | Out of Memory (OOM) | — |
| RTX 4090 24GB | 24 GB · 1008 GB/s | 68.94 GB (287%) | Out of Memory (OOM) | — |
| RTX 5090 32GB | 32 GB · 1792 GB/s | 68.94 GB (215%) | Out of Memory (OOM) | — |
| Apple M-Max 64GB | 64 GB · 546 GB/s | 67.66 GB (106%) | Out of Memory (OOM) | — |
| Mac Studio 128GB | 128 GB · 546 GB/s | 67.66 GB (53%) | Fits Comfortably | 4.6 tok/s |
| Mac Studio 192GB | 192 GB · 800 GB/s | 67.66 GB (35%) | Fits Comfortably | 6.7 tok/s |
| NVIDIA A100 80GB | 80 GB · 2039 GB/s | 68.94 GB (86%) | Tight Fit (>90% Usable) | 19.2 tok/s |
| NVIDIA H100 80GB | 80 GB · 3350 GB/s | 68.94 GB (86%) | Tight Fit (>90% Usable) | 31.6 tok/s |
Verified Transformer Architecture Parameters
- Checkpoint ID
- CohereForAI/c4ai-command-a-03-2025
- Ollama Tag
- command-a:111b
- License / Release
- CC-BY-NC-4.0 · 2025-Q1
- Topology & Attention
- Dense Transformer
- Attention Mechanism
- Hybrid Sliding-Window (SWA)
- Total Params (B)
- 111B
- Active Params / Token (B)
- 111B
- Hidden Layers / Hidden Size
- 64 / 12288
- Query Heads / KV Heads
- 96Q / 8KV (d=128)
- Sliding Window
- 4096 (75% local)
- Vocab / Max Position
- 256,000 / 262,144
Quantized formats store per-block scale factors and zero-points alongside packed integer weights. A 4-bit GGUF Q4_K_M checkpoint averages 4.85 effective bits per parameter (not 4.00), while Q8_0 averages 8.50 bpw. For Mixture-of-Experts models, all routed and shared experts remain resident in memory to prevent token-by-token host paging.
Standard Grouped-Query Attention allocates 2 × L × H_kv × d_head × S × B × bytes_kv across layers. DeepSeek Multi-head Latent Attention (MLA) compresses keys and values into L × (d_kv_lora + d_qk_rope) × S × B × bytes_kv, slashing long-context memory by over 90%. Hybrid sliding-window models cap local-attention layers at min(S, window_size) while scaling global layers linearly with S.
Quick-Start vLLM & Ollama Commands for Cohere Command A (111B)
vllm serve CohereForAI/c4ai-command-a-03-2025 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 8 \
--gpu-memory-utilization 0.95 \
--kv-cache-dtype fp8 \
--enable-prefix-caching \
--port 8000# Save as Modelfile, then run: ollama create command-a-111b-custom -f Modelfile
FROM command-a:111b
PARAMETER num_ctx 32768
PARAMETER num_batch 512
PARAMETER flash_attn true
# Environment variables for ollama serve:
# OLLAMA_NUM_PARALLEL=8 OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 ollama serveCompare Sibling & Similar-Scale Open-Weight Models
Llama 4 Scout (109B / 17B-16E MoE)
Meta Llama · 109B (HYBRID_SWA)
Mistral Large 2411 (123B)
Mistral · 123B (GQA)
Qwen2.5-72B-Instruct
Qwen · 72.7B (GQA)
DeepSeek-R1-Distill-Llama-70B
DeepSeek · 70.6B (GQA)
Llama 3.3 70B Instruct
Meta Llama · 70.6B (GQA)
DeepSeek-R1-Distill-Qwen-32B
DeepSeek · 32.8B (GQA)