👁 DeepSeek
DeepSeek
DeepSeek LLM 67B
Legacy
1.9KDownloads207LikesJan 2024Released4K tokensContextDeepSeekLicense26 EntryQuality
DeepSeek LLM 67B (67B parameters) requires approximately 48.2 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 56 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run DeepSeek LLM 67B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "deepseek-ai/deepseek-llm-67b-chat" \
--hf-file "deepseek-llm-67b-chat-Q4_K_M.gguf" \
-c 4096 -ngl 99Quick specs
Parameters67B
Architecturedense
Context4K tokens
Modalitytext
Min RAM26.1 GB
Rec. RAM40.9 GB (Q4_K_M)
LicenseDeepSeek
FamilyDeepSeek
✓ Chat✓ Reasoning
About this model
- •Home Page:: DeepSeek
- •Repository:: deepseek-ai/deepseek-LLM
- •Chat With DeepSeek LLM:: DeepSeek-LLM
Related models
Your hardware
Detecting...
Quick picks
Best budgetB
MacBook Pro M4 Max 96GB~$2,499 — 16 tok/s
Best overallB
NVIDIA H100 80GB~$40,000 — 75 tok/sBest hardware
Top picks for DeepSeek LLM 67B
Run this model
Quantization options
VRAM estimates by quant level
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 26.1 GB | Low | — |
Q3_K_S | 3 | 32.8 GB | Low | — |
NVFP4 | 4 | 37.5 GB | Medium | — |
Q4_K_M | 4 | 40.9 GB | Medium | — |
Q5_K_M | 5 | 48.2 GB | High | — |
Q6_K | 6 | 54.9 GB | High | — |
Q8_0 | 8 | 71.7 GB | Very High | — |
F16 | 16 | 137.4 GB | Maximum | — |
Quality benchmarks
DeepSeek LLM 67B benchmark scores
Coding
SWE-bench Verified—
HumanEval+73.8%
Aider Polyglot—
LiveCodeBench—
Reasoning
MMLU-Pro32.7%
GPQA Diamond8.8%
MATH-5009.3%
ARC Challenge—
General
Chatbot Arena—
IFEval55.9%
Source: official · 2024-01-05
Hardware compatibility
Fit estimates across all hardware
Computing compatibility...
Memory breakdown
Reference: RTX 2060 6GB
Weights40.9 GB
KV Cache5.8 GB
Runtime0.9 GB
Headroom0.6 GB
Frequently asked questions
FAQ — DeepSeek LLM 67B
See also